From 5e32940621eb62064d98f42c9889db71b0368bde Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Sat, 11 Jul 2015 10:02:46 -0400
Subject: libnvdimm, btt: sparse fix

Fix:
drivers/nvdimm/btt.c:635:29: warning: restricted __le64 degrades to integer

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/nvdimm/btt.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'drivers')

diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index 411c7b2bb37a..552f1c4f4dc6 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -632,8 +632,9 @@ static void parse_arena_meta(struct arena_info *arena, struct btt_sb *super,
 	arena->logoff = arena_off + le64_to_cpu(super->logoff);
 	arena->info2off = arena_off + le64_to_cpu(super->info2off);
 
-	arena->size = (super->nextoff > 0) ? (le64_to_cpu(super->nextoff)) :
-			(arena->info2off - arena->infooff + BTT_PG_SIZE);
+	arena->size = (le64_to_cpu(super->nextoff) > 0)
+		? (le64_to_cpu(super->nextoff))
+		: (arena->info2off - arena->infooff + BTT_PG_SIZE);
 
 	arena->flags = le32_to_cpu(super->flags);
 }
-- 
cgit v1.2.3


From 39c686b862cdb2049b90e095b6c6c727b2a7ab60 Mon Sep 17 00:00:00 2001
From: Vishal Verma <vishal.l.verma@intel.com>
Date: Thu, 9 Jul 2015 13:25:36 -0600
Subject: libnvdimm: Add DSM support for Address Range Scrub commands

Add support for the three ARS DSM commands:
- Query ARS Capabilities - Queries the firmware to check if a given
  range supports scrub, and if so, which type (persistent vs. volatile)
- Start ARS - Starts a scrub for a given range/type
- Query ARS Status - Checks status of a previously started scrub, and
  provides the error logs if any.

  The commands are described by the example DSM spec at:
  http://pmem.io/documents/NVDIMM_DSM_Interface_Example.pdf

Also add these commands to the nfit_test test framework, and return
canned data.

Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/acpi/nfit.c | 1 +
 drivers/acpi/nfit.h | 1 +
 2 files changed, 2 insertions(+)

(limited to 'drivers')

diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c
index 628a42c41ab1..ef8a664db254 100644
--- a/drivers/acpi/nfit.c
+++ b/drivers/acpi/nfit.c
@@ -868,6 +868,7 @@ static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc)
 	struct acpi_device *adev;
 	int i;
 
+	nd_desc->dsm_mask = acpi_desc->bus_dsm_force_en;
 	adev = to_acpi_dev(acpi_desc);
 	if (!adev)
 		return;
diff --git a/drivers/acpi/nfit.h b/drivers/acpi/nfit.h
index 79b6d83875c1..f2c2bb751882 100644
--- a/drivers/acpi/nfit.h
+++ b/drivers/acpi/nfit.h
@@ -107,6 +107,7 @@ struct acpi_nfit_desc {
 	struct nvdimm_bus *nvdimm_bus;
 	struct device *dev;
 	unsigned long dimm_dsm_force_en;
+	unsigned long bus_dsm_force_en;
 	int (*blk_do_io)(struct nd_blk_region *ndbr, resource_size_t dpa,
 			void *iobuf, u64 len, int rw);
 };
-- 
cgit v1.2.3


From 6b47496a6fc81816e7edaf8224dfb88e402a05f5 Mon Sep 17 00:00:00 2001
From: Vishal Verma <vishal.l.verma@intel.com>
Date: Thu, 23 Jul 2015 11:58:48 -0600
Subject: libnvdimm, pmem: Change pmem physical sector size to PAGE_SIZE

Based on a patch: c8fa317 brd: Request from fdisk 4k alignment by Boaz
Harrosh, allow fdisk to create properly aligned partitions for DAX. This
will also cause mkfs.ext4 to emit a warning if using a file system block
size of less than PAGE_SIZE.

Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Matthew Wilcox <matthew.r.wilcox@intel.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Elliott, Robert <Elliott@hp.com>
Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
Acked-by: Boaz Harrosh <boaz@plexistor.com>
Acked-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/nvdimm/pmem.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'drivers')

diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index ade9eb917a4d..bcf48f133443 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -162,6 +162,7 @@ static int pmem_attach_disk(struct nd_namespace_common *ndns,
 		return -ENOMEM;
 
 	blk_queue_make_request(pmem->pmem_queue, pmem_make_request);
+	blk_queue_physical_block_size(pmem->pmem_queue, PAGE_SIZE);
 	blk_queue_max_hw_sectors(pmem->pmem_queue, UINT_MAX);
 	blk_queue_bounce_limit(pmem->pmem_queue, BLK_BOUNCE_ANY);
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, pmem->pmem_queue);
-- 
cgit v1.2.3


From 60e95f43fc8573e81f54b0c1e0bc542c2260d956 Mon Sep 17 00:00:00 2001
From: Linda Knippers <linda.knippers@hp.com>
Date: Wed, 22 Jul 2015 16:17:22 -0400
Subject: nfit: Don't check _STA on NVDIMM devices

The _STA only applies to the root device, not the individual NVDIMMS,
so don't check here. NVDIMM device state flags are checked elsewhere.

Signed-off-by: Linda Knippers <linda.knippers@hp.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/acpi/nfit.c | 20 ++------------------
 1 file changed, 2 insertions(+), 18 deletions(-)

(limited to 'drivers')

diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c
index ef8a664db254..7c2638f914a9 100644
--- a/drivers/acpi/nfit.c
+++ b/drivers/acpi/nfit.c
@@ -764,9 +764,7 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 	struct acpi_device *adev, *adev_dimm;
 	struct device *dev = acpi_desc->dev;
 	const u8 *uuid = to_nfit_uuid(NFIT_DEV_DIMM);
-	unsigned long long sta;
-	int i, rc = -ENODEV;
-	acpi_status status;
+	int i;
 
 	nfit_mem->dsm_mask = acpi_desc->dimm_dsm_force_en;
 	adev = to_acpi_dev(acpi_desc);
@@ -781,25 +779,11 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 		return force_enable_dimms ? 0 : -ENODEV;
 	}
 
-	status = acpi_evaluate_integer(adev_dimm->handle, "_STA", NULL, &sta);
-	if (status == AE_NOT_FOUND) {
-		dev_dbg(dev, "%s missing _STA, assuming enabled...\n",
-				dev_name(&adev_dimm->dev));
-		rc = 0;
-	} else if (ACPI_FAILURE(status))
-		dev_err(dev, "%s failed to retrieve_STA, disabling...\n",
-				dev_name(&adev_dimm->dev));
-	else if ((sta & ACPI_STA_DEVICE_ENABLED) == 0)
-		dev_info(dev, "%s disabled by firmware\n",
-				dev_name(&adev_dimm->dev));
-	else
-		rc = 0;
-
 	for (i = ND_CMD_SMART; i <= ND_CMD_VENDOR; i++)
 		if (acpi_check_dsm(adev_dimm->handle, uuid, 1, 1ULL << i))
 			set_bit(i, &nfit_mem->dsm_mask);
 
-	return force_enable_dimms ? 0 : rc;
+	return 0;
 }
 
 static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc)
-- 
cgit v1.2.3


From f6ef5a2a50816b58e3126206de13d0b9fdf89df5 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 28 Jul 2015 12:27:01 -0700
Subject: nvdimm: fix inline function return type warning

Fix multiple build warnings when CONFIG_BTT is not enabled:

In file included from ../drivers/nvdimm/bus.c:29:0:
../drivers/nvdimm/nd.h:169:15: warning: return type defaults to 'int' [-Wreturn-type]
 static inline nd_btt_probe(struct nd_namespace_common *ndns, void *drvdata)
               ^

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: linux-nvdimm@lists.01.org
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/nvdimm/nd.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers')

diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
index c41f53e74277..835263e47bb8 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -166,7 +166,7 @@ int nd_btt_probe(struct nd_namespace_common *ndns, void *drvdata);
 bool is_nd_btt(struct device *dev);
 struct device *nd_btt_create(struct nd_region *nd_region);
 #else
-static inline nd_btt_probe(struct nd_namespace_common *ndns, void *drvdata)
+static inline int nd_btt_probe(struct nd_namespace_common *ndns, void *drvdata)
 {
 	return -ENODEV;
 }
-- 
cgit v1.2.3


From 2584cf83578c26db144730ef498f4070f82ee3ea Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Mon, 10 Aug 2015 23:07:05 -0400
Subject: arch, drivers: don't include <asm/io.h> directly, use <linux/io.h>
 instead

Preparation for uniform definition of ioremap, ioremap_wc, ioremap_wt,
and ioremap_cache, tree-wide.

Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/isdn/icn/icn.h                      | 2 +-
 drivers/mtd/devices/slram.c                 | 2 +-
 drivers/mtd/nand/diskonchip.c               | 2 +-
 drivers/mtd/onenand/generic.c               | 2 +-
 drivers/scsi/sun3x_esp.c                    | 2 +-
 drivers/staging/comedi/drivers/ii_pci20kc.c | 1 +
 drivers/tty/serial/8250/8250_core.c         | 2 +-
 drivers/video/fbdev/s1d13xxxfb.c            | 3 +--
 drivers/video/fbdev/stifb.c                 | 1 +
 9 files changed, 9 insertions(+), 8 deletions(-)

(limited to 'drivers')

diff --git a/drivers/isdn/icn/icn.h b/drivers/isdn/icn/icn.h
index b713466997a0..f8f2e76d34bf 100644
--- a/drivers/isdn/icn/icn.h
+++ b/drivers/isdn/icn/icn.h
@@ -38,7 +38,7 @@ typedef struct icn_cdef {
 #include <linux/errno.h>
 #include <linux/fs.h>
 #include <linux/major.h>
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/kernel.h>
 #include <linux/signal.h>
 #include <linux/slab.h>
diff --git a/drivers/mtd/devices/slram.c b/drivers/mtd/devices/slram.c
index 2fc4957cbe7f..a70eb83e68f1 100644
--- a/drivers/mtd/devices/slram.c
+++ b/drivers/mtd/devices/slram.c
@@ -41,7 +41,7 @@
 #include <linux/fs.h>
 #include <linux/ioctl.h>
 #include <linux/init.h>
-#include <asm/io.h>
+#include <linux/io.h>
 
 #include <linux/mtd/mtd.h>
 
diff --git a/drivers/mtd/nand/diskonchip.c b/drivers/mtd/nand/diskonchip.c
index 7da266a53979..0802158a3f75 100644
--- a/drivers/mtd/nand/diskonchip.c
+++ b/drivers/mtd/nand/diskonchip.c
@@ -24,7 +24,7 @@
 #include <linux/rslib.h>
 #include <linux/moduleparam.h>
 #include <linux/slab.h>
-#include <asm/io.h>
+#include <linux/io.h>
 
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/nand.h>
diff --git a/drivers/mtd/onenand/generic.c b/drivers/mtd/onenand/generic.c
index 32a216d31141..ab7bda0bb245 100644
--- a/drivers/mtd/onenand/generic.c
+++ b/drivers/mtd/onenand/generic.c
@@ -18,7 +18,7 @@
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/onenand.h>
 #include <linux/mtd/partitions.h>
-#include <asm/io.h>
+#include <linux/io.h>
 
 /*
  * Note: Driver name and platform data format have been updated!
diff --git a/drivers/scsi/sun3x_esp.c b/drivers/scsi/sun3x_esp.c
index e26e81de7c45..d50c5ed8f428 100644
--- a/drivers/scsi/sun3x_esp.c
+++ b/drivers/scsi/sun3x_esp.c
@@ -12,9 +12,9 @@
 #include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
 #include <linux/interrupt.h>
+#include <linux/io.h>
 
 #include <asm/sun3x.h>
-#include <asm/io.h>
 #include <asm/dma.h>
 #include <asm/dvma.h>
 
diff --git a/drivers/staging/comedi/drivers/ii_pci20kc.c b/drivers/staging/comedi/drivers/ii_pci20kc.c
index 0768bc42a5db..14ef1f67dd42 100644
--- a/drivers/staging/comedi/drivers/ii_pci20kc.c
+++ b/drivers/staging/comedi/drivers/ii_pci20kc.c
@@ -28,6 +28,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/io.h>
 #include "../comedidev.h"
 
 /*
diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index 37fff12dd4d0..fe902ff52e58 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -38,11 +38,11 @@
 #include <linux/slab.h>
 #include <linux/uaccess.h>
 #include <linux/pm_runtime.h>
+#include <linux/io.h>
 #ifdef CONFIG_SPARC
 #include <linux/sunserialcore.h>
 #endif
 
-#include <asm/io.h>
 #include <asm/irq.h>
 
 #include "8250.h"
diff --git a/drivers/video/fbdev/s1d13xxxfb.c b/drivers/video/fbdev/s1d13xxxfb.c
index 83433cb0dfba..96aa46dc696c 100644
--- a/drivers/video/fbdev/s1d13xxxfb.c
+++ b/drivers/video/fbdev/s1d13xxxfb.c
@@ -32,8 +32,7 @@
 #include <linux/spinlock_types.h>
 #include <linux/spinlock.h>
 #include <linux/slab.h>
-
-#include <asm/io.h>
+#include <linux/io.h>
 
 #include <video/s1d13xxxfb.h>
 
diff --git a/drivers/video/fbdev/stifb.c b/drivers/video/fbdev/stifb.c
index 735355b0e023..7df4228e25f0 100644
--- a/drivers/video/fbdev/stifb.c
+++ b/drivers/video/fbdev/stifb.c
@@ -64,6 +64,7 @@
 #include <linux/fb.h>
 #include <linux/init.h>
 #include <linux/ioport.h>
+#include <linux/io.h>
 
 #include <asm/grfioctl.h>	/* for HP-UX compatibility */
 #include <asm/uaccess.h>
-- 
cgit v1.2.3


From 92b19ff50e8f242392d78b2aacc5b5b672f1796b Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Mon, 10 Aug 2015 23:07:06 -0400
Subject: cleanup IORESOURCE_CACHEABLE vs ioremap()

Quoting Arnd:
    I was thinking the opposite approach and basically removing all uses
    of IORESOURCE_CACHEABLE from the kernel. There are only a handful of
    them.and we can probably replace them all with hardcoded
    ioremap_cached() calls in the cases they are actually useful.

All existing usages of IORESOURCE_CACHEABLE call ioremap() instead of
ioremap_nocache() if the resource is cacheable, however ioremap() is
uncached by default. Clearly none of the existing usages care about the
cacheability. Particularly devm_ioremap_resource() never worked as
advertised since it always fell back to plain ioremap().

Clean this up as the new direction we want is to convert
ioremap_<type>() usages to memremap(..., flags).

Suggested-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/pci/probe.c                 |  3 +--
 drivers/pnp/manager.c               |  2 --
 drivers/scsi/aic94xx/aic94xx_init.c |  7 +------
 drivers/scsi/arcmsr/arcmsr_hba.c    |  5 +----
 drivers/scsi/mvsas/mv_init.c        | 15 ++++-----------
 drivers/video/fbdev/ocfb.c          |  1 -
 6 files changed, 7 insertions(+), 26 deletions(-)

(limited to 'drivers')

diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index cefd636681b6..8ed37dd04056 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -326,8 +326,7 @@ static void pci_read_bases(struct pci_dev *dev, unsigned int howmany, int rom)
 		struct resource *res = &dev->resource[PCI_ROM_RESOURCE];
 		dev->rom_base_reg = rom;
 		res->flags = IORESOURCE_MEM | IORESOURCE_PREFETCH |
-				IORESOURCE_READONLY | IORESOURCE_CACHEABLE |
-				IORESOURCE_SIZEALIGN;
+				IORESOURCE_READONLY | IORESOURCE_SIZEALIGN;
 		__pci_read_base(dev, pci_bar_mem32, res, rom);
 	}
 }
diff --git a/drivers/pnp/manager.c b/drivers/pnp/manager.c
index 9357aa779048..7ad3295752ef 100644
--- a/drivers/pnp/manager.c
+++ b/drivers/pnp/manager.c
@@ -97,8 +97,6 @@ static int pnp_assign_mem(struct pnp_dev *dev, struct pnp_mem *rule, int idx)
 	/* ??? rule->flags restricted to 8 bits, all tests bogus ??? */
 	if (!(rule->flags & IORESOURCE_MEM_WRITEABLE))
 		res->flags |= IORESOURCE_READONLY;
-	if (rule->flags & IORESOURCE_MEM_CACHEABLE)
-		res->flags |= IORESOURCE_CACHEABLE;
 	if (rule->flags & IORESOURCE_MEM_RANGELENGTH)
 		res->flags |= IORESOURCE_RANGELENGTH;
 	if (rule->flags & IORESOURCE_MEM_SHADOWABLE)
diff --git a/drivers/scsi/aic94xx/aic94xx_init.c b/drivers/scsi/aic94xx/aic94xx_init.c
index 4b135cca42a1..140cb8e6fea2 100644
--- a/drivers/scsi/aic94xx/aic94xx_init.c
+++ b/drivers/scsi/aic94xx/aic94xx_init.c
@@ -100,12 +100,7 @@ static int asd_map_memio(struct asd_ha_struct *asd_ha)
 				   pci_name(asd_ha->pcidev));
 			goto Err;
 		}
-		if (io_handle->flags & IORESOURCE_CACHEABLE)
-			io_handle->addr = ioremap(io_handle->start,
-						  io_handle->len);
-		else
-			io_handle->addr = ioremap_nocache(io_handle->start,
-							  io_handle->len);
+		io_handle->addr = ioremap(io_handle->start, io_handle->len);
 		if (!io_handle->addr) {
 			asd_printk("couldn't map MBAR%d of %s\n", i==0?0:1,
 				   pci_name(asd_ha->pcidev));
diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c
index 914c39f9f388..e4f77cad9fd8 100644
--- a/drivers/scsi/arcmsr/arcmsr_hba.c
+++ b/drivers/scsi/arcmsr/arcmsr_hba.c
@@ -259,10 +259,7 @@ static bool arcmsr_remap_pciregion(struct AdapterControlBlock *acb)
 		addr = (unsigned long)pci_resource_start(pdev, 0);
 		range = pci_resource_len(pdev, 0);
 		flags = pci_resource_flags(pdev, 0);
-		if (flags & IORESOURCE_CACHEABLE)
-			mem_base0 = ioremap(addr, range);
-		else
-			mem_base0 = ioremap_nocache(addr, range);
+		mem_base0 = ioremap(addr, range);
 		if (!mem_base0) {
 			pr_notice("arcmsr%d: memory mapping region fail\n",
 				acb->host->host_no);
diff --git a/drivers/scsi/mvsas/mv_init.c b/drivers/scsi/mvsas/mv_init.c
index d40d734aa53a..e654b5cec69e 100644
--- a/drivers/scsi/mvsas/mv_init.c
+++ b/drivers/scsi/mvsas/mv_init.c
@@ -324,13 +324,9 @@ int mvs_ioremap(struct mvs_info *mvi, int bar, int bar_ex)
 			goto err_out;
 
 		res_flag_ex = pci_resource_flags(pdev, bar_ex);
-		if (res_flag_ex & IORESOURCE_MEM) {
-			if (res_flag_ex & IORESOURCE_CACHEABLE)
-				mvi->regs_ex = ioremap(res_start, res_len);
-			else
-				mvi->regs_ex = ioremap_nocache(res_start,
-						res_len);
-		} else
+		if (res_flag_ex & IORESOURCE_MEM)
+			mvi->regs_ex = ioremap(res_start, res_len);
+		else
 			mvi->regs_ex = (void *)res_start;
 		if (!mvi->regs_ex)
 			goto err_out;
@@ -342,10 +338,7 @@ int mvs_ioremap(struct mvs_info *mvi, int bar, int bar_ex)
 		goto err_out;
 
 	res_flag = pci_resource_flags(pdev, bar);
-	if (res_flag & IORESOURCE_CACHEABLE)
-		mvi->regs = ioremap(res_start, res_len);
-	else
-		mvi->regs = ioremap_nocache(res_start, res_len);
+	mvi->regs = ioremap(res_start, res_len);
 
 	if (!mvi->regs) {
 		if (mvi->regs_ex && (res_flag_ex & IORESOURCE_MEM))
diff --git a/drivers/video/fbdev/ocfb.c b/drivers/video/fbdev/ocfb.c
index de9819660ca0..c9293aea8ec3 100644
--- a/drivers/video/fbdev/ocfb.c
+++ b/drivers/video/fbdev/ocfb.c
@@ -325,7 +325,6 @@ static int ocfb_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev, "I/O resource request failed\n");
 		return -ENXIO;
 	}
-	res->flags &= ~IORESOURCE_CACHEABLE;
 	fbdev->regs = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(fbdev->regs))
 		return PTR_ERR(fbdev->regs);
-- 
cgit v1.2.3


From 3103dc0304fd9c8ab576977cd98140d4fbac1730 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Mon, 10 Aug 2015 23:07:06 -0400
Subject: visorbus: switch from ioremap_cache to memremap

In preparation for deprecating ioremap_cache() convert its usage in
visorbus to memremap.

Cc: Benjamin Romer <benjamin.romer@unisys.com>
Cc: David Kershner <david.kershner@unisys.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/staging/unisys/visorbus/visorchannel.c | 16 +++++++++-------
 drivers/staging/unisys/visorbus/visorchipset.c | 17 +++++++++--------
 2 files changed, 18 insertions(+), 15 deletions(-)

(limited to 'drivers')

diff --git a/drivers/staging/unisys/visorbus/visorchannel.c b/drivers/staging/unisys/visorbus/visorchannel.c
index 20b63496e9f2..19c4a78a3617 100644
--- a/drivers/staging/unisys/visorbus/visorchannel.c
+++ b/drivers/staging/unisys/visorbus/visorchannel.c
@@ -21,6 +21,7 @@
  */
 
 #include <linux/uuid.h>
+#include <linux/io.h>
 
 #include "version.h"
 #include "visorbus.h"
@@ -36,7 +37,7 @@ static const uuid_le spar_video_guid = SPAR_CONSOLEVIDEO_CHANNEL_PROTOCOL_GUID;
 struct visorchannel {
 	u64 physaddr;
 	ulong nbytes;
-	void __iomem *mapped;
+	void *mapped;
 	bool requested;
 	struct channel_header chan_hdr;
 	uuid_le guid;
@@ -93,7 +94,7 @@ visorchannel_create_guts(u64 physaddr, unsigned long channel_bytes,
 		}
 	}
 
-	channel->mapped = ioremap_cache(physaddr, size);
+	channel->mapped = memremap(physaddr, size, MEMREMAP_WB);
 	if (!channel->mapped) {
 		release_mem_region(physaddr, size);
 		goto cleanup;
@@ -113,7 +114,7 @@ visorchannel_create_guts(u64 physaddr, unsigned long channel_bytes,
 	if (uuid_le_cmp(guid, NULL_UUID_LE) == 0)
 		guid = channel->chan_hdr.chtype;
 
-	iounmap(channel->mapped);
+	memunmap(channel->mapped);
 	if (channel->requested)
 		release_mem_region(channel->physaddr, channel->nbytes);
 	channel->mapped = NULL;
@@ -126,7 +127,8 @@ visorchannel_create_guts(u64 physaddr, unsigned long channel_bytes,
 		}
 	}
 
-	channel->mapped = ioremap_cache(channel->physaddr, channel_bytes);
+	channel->mapped = memremap(channel->physaddr, channel_bytes,
+			MEMREMAP_WB);
 	if (!channel->mapped) {
 		release_mem_region(channel->physaddr, channel_bytes);
 		goto cleanup;
@@ -167,7 +169,7 @@ visorchannel_destroy(struct visorchannel *channel)
 	if (!channel)
 		return;
 	if (channel->mapped) {
-		iounmap(channel->mapped);
+		memunmap(channel->mapped);
 		if (channel->requested)
 			release_mem_region(channel->physaddr, channel->nbytes);
 	}
@@ -241,7 +243,7 @@ visorchannel_read(struct visorchannel *channel, ulong offset,
 	if (offset + nbytes > channel->nbytes)
 		return -EIO;
 
-	memcpy_fromio(local, channel->mapped + offset, nbytes);
+	memcpy(local, channel->mapped + offset, nbytes);
 
 	return 0;
 }
@@ -262,7 +264,7 @@ visorchannel_write(struct visorchannel *channel, ulong offset,
 		memcpy(&channel->chan_hdr + offset, local, copy_size);
 	}
 
-	memcpy_toio(channel->mapped + offset, local, nbytes);
+	memcpy(channel->mapped + offset, local, nbytes);
 
 	return 0;
 }
diff --git a/drivers/staging/unisys/visorbus/visorchipset.c b/drivers/staging/unisys/visorbus/visorchipset.c
index bb8087e70127..e3c55ccf929b 100644
--- a/drivers/staging/unisys/visorbus/visorchipset.c
+++ b/drivers/staging/unisys/visorbus/visorchipset.c
@@ -119,7 +119,7 @@ static struct visorchannel *controlvm_channel;
 
 /* Manages the request payload in the controlvm channel */
 struct visor_controlvm_payload_info {
-	u8 __iomem *ptr;	/* pointer to base address of payload pool */
+	u8 *ptr;		/* pointer to base address of payload pool */
 	u64 offset;		/* offset from beginning of controlvm
 				 * channel to beginning of payload * pool */
 	u32 bytes;		/* number of bytes in payload pool */
@@ -401,21 +401,22 @@ parser_init_byte_stream(u64 addr, u32 bytes, bool local, bool *retry)
 		p = __va((unsigned long) (addr));
 		memcpy(ctx->data, p, bytes);
 	} else {
-		void __iomem *mapping;
+		void *mapping;
 
 		if (!request_mem_region(addr, bytes, "visorchipset")) {
 			rc = NULL;
 			goto cleanup;
 		}
 
-		mapping = ioremap_cache(addr, bytes);
+		mapping = memremap(addr, bytes, MEMREMAP_WB);
 		if (!mapping) {
 			release_mem_region(addr, bytes);
 			rc = NULL;
 			goto cleanup;
 		}
-		memcpy_fromio(ctx->data, mapping, bytes);
+		memcpy(ctx->data, mapping, bytes);
 		release_mem_region(addr, bytes);
+		memunmap(mapping);
 	}
 
 	ctx->byte_stream = true;
@@ -1327,7 +1328,7 @@ static int
 initialize_controlvm_payload_info(u64 phys_addr, u64 offset, u32 bytes,
 				  struct visor_controlvm_payload_info *info)
 {
-	u8 __iomem *payload = NULL;
+	u8 *payload = NULL;
 	int rc = CONTROLVM_RESP_SUCCESS;
 
 	if (!info) {
@@ -1339,7 +1340,7 @@ initialize_controlvm_payload_info(u64 phys_addr, u64 offset, u32 bytes,
 		rc = -CONTROLVM_RESP_ERROR_PAYLOAD_INVALID;
 		goto cleanup;
 	}
-	payload = ioremap_cache(phys_addr + offset, bytes);
+	payload = memremap(phys_addr + offset, bytes, MEMREMAP_WB);
 	if (!payload) {
 		rc = -CONTROLVM_RESP_ERROR_IOREMAP_FAILED;
 		goto cleanup;
@@ -1352,7 +1353,7 @@ initialize_controlvm_payload_info(u64 phys_addr, u64 offset, u32 bytes,
 cleanup:
 	if (rc < 0) {
 		if (payload) {
-			iounmap(payload);
+			memunmap(payload);
 			payload = NULL;
 		}
 	}
@@ -1363,7 +1364,7 @@ static void
 destroy_controlvm_payload_info(struct visor_controlvm_payload_info *info)
 {
 	if (info->ptr) {
-		iounmap(info->ptr);
+		memunmap(info->ptr);
 		info->ptr = NULL;
 	}
 	memset(info, 0, sizeof(struct visor_controlvm_payload_info));
-- 
cgit v1.2.3


From fbde1414acc0440024083bf0c391b259bcfc4826 Mon Sep 17 00:00:00 2001
From: Vishal Verma <vishal.l.verma@intel.com>
Date: Wed, 29 Jul 2015 14:58:07 -0600
Subject: libnvdimm, btt: clean up internal interfaces

Consolidate the parameters passed to arena_is_valid into just nd_btt,
and an info block to increase re-usability.

Similarly, btt_arena_write_layout doesn't need to be passed a uuid, as
it can be obtained from arena->nd_btt.

Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/nvdimm/btt.c | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

(limited to 'drivers')

diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index 552f1c4f4dc6..87e6a96a6c19 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -585,12 +585,11 @@ static void free_arenas(struct btt *btt)
 /*
  * This function checks if the metadata layout is valid and error free
  */
-static int arena_is_valid(struct arena_info *arena, struct btt_sb *super,
-				u8 *uuid, u32 lbasize)
+static int arena_is_valid(struct nd_btt *nd_btt, struct btt_sb *super)
 {
 	u64 checksum;
 
-	if (memcmp(super->uuid, uuid, 16))
+	if (memcmp(super->uuid, nd_btt->uuid, 16))
 		return 0;
 
 	checksum = le64_to_cpu(super->checksum);
@@ -599,12 +598,12 @@ static int arena_is_valid(struct arena_info *arena, struct btt_sb *super,
 		return 0;
 	super->checksum = cpu_to_le64(checksum);
 
-	if (lbasize != le32_to_cpu(super->external_lbasize))
+	if (nd_btt->lbasize != le32_to_cpu(super->external_lbasize))
 		return 0;
 
 	/* TODO: figure out action for this */
 	if ((le32_to_cpu(super->flags) & IB_FLAG_ERROR_MASK) != 0)
-		dev_info(to_dev(arena), "Found arena with an error flag\n");
+		dev_info(&nd_btt->dev, "Found arena with an error flag\n");
 
 	return 1;
 }
@@ -666,8 +665,7 @@ static int discover_arenas(struct btt *btt)
 		if (ret)
 			goto out;
 
-		if (!arena_is_valid(arena, super, btt->nd_btt->uuid,
-				btt->lbasize)) {
+		if (!arena_is_valid(btt->nd_btt, super)) {
 			if (remaining == btt->rawsize) {
 				btt->init_state = INIT_NOTFOUND;
 				dev_info(to_dev(arena), "No existing arenas\n");
@@ -756,10 +754,11 @@ static int create_arenas(struct btt *btt)
  * It is only called for an uninitialized arena when a write
  * to that arena occurs for the first time.
  */
-static int btt_arena_write_layout(struct arena_info *arena, u8 *uuid)
+static int btt_arena_write_layout(struct arena_info *arena)
 {
 	int ret;
 	struct btt_sb *super;
+	struct nd_btt *nd_btt = arena->nd_btt;
 
 	ret = btt_map_init(arena);
 	if (ret)
@@ -774,7 +773,7 @@ static int btt_arena_write_layout(struct arena_info *arena, u8 *uuid)
 		return -ENOMEM;
 
 	strncpy(super->signature, BTT_SIG, BTT_SIG_LEN);
-	memcpy(super->uuid, uuid, 16);
+	memcpy(super->uuid, nd_btt->uuid, 16);
 	super->flags = cpu_to_le32(arena->flags);
 	super->version_major = cpu_to_le16(arena->version_major);
 	super->version_minor = cpu_to_le16(arena->version_minor);
@@ -814,7 +813,7 @@ static int btt_meta_init(struct btt *btt)
 
 	mutex_lock(&btt->init_lock);
 	list_for_each_entry(arena, &btt->arena_list, list) {
-		ret = btt_arena_write_layout(arena, btt->nd_btt->uuid);
+		ret = btt_arena_write_layout(arena);
 		if (ret)
 			goto unlock;
 
-- 
cgit v1.2.3


From ab45e7632717b811e0786e46ca5ad279cb731b66 Mon Sep 17 00:00:00 2001
From: Vishal Verma <vishal.l.verma@intel.com>
Date: Wed, 29 Jul 2015 14:58:08 -0600
Subject: libnvdimm, btt: consolidate arena validation

Use arena_is_valid as a common routine for checking the validity of an
info block from both discover_arenas, and nd_btt_probe.

As a result, don't check for validity of the BTT's UUID, and lbasize.
The checksum in the BTT info block guarantees self-consistency, and when
we're called from nd_btt_probe, we don't have a valid uuid or lbasize
available to check against.

Also cleanup to return a bool instead of an int.

Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/nvdimm/btt.c      | 28 +---------------------------
 drivers/nvdimm/btt.h      |  3 +++
 drivers/nvdimm/btt_devs.c | 42 +++++++++++++++++++++++++++++++++---------
 3 files changed, 37 insertions(+), 36 deletions(-)

(limited to 'drivers')

diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index 87e6a96a6c19..6567746aa315 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -582,32 +582,6 @@ static void free_arenas(struct btt *btt)
 	}
 }
 
-/*
- * This function checks if the metadata layout is valid and error free
- */
-static int arena_is_valid(struct nd_btt *nd_btt, struct btt_sb *super)
-{
-	u64 checksum;
-
-	if (memcmp(super->uuid, nd_btt->uuid, 16))
-		return 0;
-
-	checksum = le64_to_cpu(super->checksum);
-	super->checksum = 0;
-	if (checksum != nd_btt_sb_checksum(super))
-		return 0;
-	super->checksum = cpu_to_le64(checksum);
-
-	if (nd_btt->lbasize != le32_to_cpu(super->external_lbasize))
-		return 0;
-
-	/* TODO: figure out action for this */
-	if ((le32_to_cpu(super->flags) & IB_FLAG_ERROR_MASK) != 0)
-		dev_info(&nd_btt->dev, "Found arena with an error flag\n");
-
-	return 1;
-}
-
 /*
  * This function reads an existing valid btt superblock and
  * populates the corresponding arena_info struct
@@ -665,7 +639,7 @@ static int discover_arenas(struct btt *btt)
 		if (ret)
 			goto out;
 
-		if (!arena_is_valid(btt->nd_btt, super)) {
+		if (!nd_btt_arena_is_valid(btt->nd_btt, super)) {
 			if (remaining == btt->rawsize) {
 				btt->init_state = INIT_NOTFOUND;
 				dev_info(to_dev(arena), "No existing arenas\n");
diff --git a/drivers/nvdimm/btt.h b/drivers/nvdimm/btt.h
index 75b0d80a6bd9..b2f8651e5395 100644
--- a/drivers/nvdimm/btt.h
+++ b/drivers/nvdimm/btt.h
@@ -182,4 +182,7 @@ struct btt {
 	int init_state;
 	int num_arenas;
 };
+
+bool nd_btt_arena_is_valid(struct nd_btt *nd_btt, struct btt_sb *super);
+
 #endif
diff --git a/drivers/nvdimm/btt_devs.c b/drivers/nvdimm/btt_devs.c
index 6ac8c0fea3ec..18e0663e922c 100644
--- a/drivers/nvdimm/btt_devs.c
+++ b/drivers/nvdimm/btt_devs.c
@@ -342,6 +342,38 @@ struct device *nd_btt_create(struct nd_region *nd_region)
 	return dev;
 }
 
+/**
+ * nd_btt_arena_is_valid - check if the metadata layout is valid
+ * @nd_btt:	device with BTT geometry and backing device info
+ * @super:	pointer to the arena's info block being tested
+ *
+ * Check consistency of the btt info block with itself by validating
+ * the checksum.
+ *
+ * Returns:
+ * false for an invalid info block, true for a valid one
+ */
+bool nd_btt_arena_is_valid(struct nd_btt *nd_btt, struct btt_sb *super)
+{
+	u64 checksum;
+
+	if (memcmp(super->signature, BTT_SIG, BTT_SIG_LEN) != 0)
+		return false;
+
+	checksum = le64_to_cpu(super->checksum);
+	super->checksum = 0;
+	if (checksum != nd_btt_sb_checksum(super))
+		return false;
+	super->checksum = cpu_to_le64(checksum);
+
+	/* TODO: figure out action for this */
+	if ((le32_to_cpu(super->flags) & IB_FLAG_ERROR_MASK) != 0)
+		dev_info(&nd_btt->dev, "Found arena with an error flag\n");
+
+	return true;
+}
+EXPORT_SYMBOL(nd_btt_arena_is_valid);
+
 /*
  * nd_btt_sb_checksum: compute checksum for btt info block
  *
@@ -364,8 +396,6 @@ EXPORT_SYMBOL(nd_btt_sb_checksum);
 static int __nd_btt_probe(struct nd_btt *nd_btt,
 		struct nd_namespace_common *ndns, struct btt_sb *btt_sb)
 {
-	u64 checksum;
-
 	if (!btt_sb || !ndns || !nd_btt)
 		return -ENODEV;
 
@@ -375,14 +405,8 @@ static int __nd_btt_probe(struct nd_btt *nd_btt,
 	if (nvdimm_namespace_capacity(ndns) < SZ_16M)
 		return -ENXIO;
 
-	if (memcmp(btt_sb->signature, BTT_SIG, BTT_SIG_LEN) != 0)
-		return -ENODEV;
-
-	checksum = le64_to_cpu(btt_sb->checksum);
-	btt_sb->checksum = 0;
-	if (checksum != nd_btt_sb_checksum(btt_sb))
+	if (!nd_btt_arena_is_valid(nd_btt, btt_sb))
 		return -ENODEV;
-	btt_sb->checksum = cpu_to_le64(checksum);
 
 	nd_btt->lbasize = le32_to_cpu(btt_sb->external_lbasize);
 	nd_btt->uuid = kmemdup(btt_sb->uuid, 16, GFP_KERNEL);
-- 
cgit v1.2.3


From 6ec689542b5bc516187917d49b112847dfb75b0b Mon Sep 17 00:00:00 2001
From: Vishal Verma <vishal.l.verma@intel.com>
Date: Wed, 29 Jul 2015 14:58:09 -0600
Subject: libnvdimm, btt: write and validate parent_uuid

When a BTT is instantiated on a namespace it must validate the namespace
uuid matches the 'parent_uuid' stored in the btt superblock. This
property enforces that changing the namespace UUID invalidates all
former BTT instances on that storage. For "IO namespaces" that don't
have a label or UUID, the parent_uuid is set to zero, and this
validation is skipped. For such cases, old BTTs have to be invalidated
by forcing the namespace to raw mode, and overwriting the BTT info
blocks.

Based on a patch by Dan Williams <dan.j.williams@intel.com>

Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/nvdimm/btt.c            |  2 ++
 drivers/nvdimm/btt_devs.c       | 15 ++++++++++++++-
 drivers/nvdimm/namespace_devs.c | 20 ++++++++++++++++++++
 drivers/nvdimm/nd.h             |  1 +
 4 files changed, 37 insertions(+), 1 deletion(-)

(limited to 'drivers')

diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index 6567746aa315..19588291550b 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -733,6 +733,7 @@ static int btt_arena_write_layout(struct arena_info *arena)
 	int ret;
 	struct btt_sb *super;
 	struct nd_btt *nd_btt = arena->nd_btt;
+	const u8 *parent_uuid = nd_dev_to_uuid(&nd_btt->ndns->dev);
 
 	ret = btt_map_init(arena);
 	if (ret)
@@ -748,6 +749,7 @@ static int btt_arena_write_layout(struct arena_info *arena)
 
 	strncpy(super->signature, BTT_SIG, BTT_SIG_LEN);
 	memcpy(super->uuid, nd_btt->uuid, 16);
+	memcpy(super->parent_uuid, parent_uuid, 16);
 	super->flags = cpu_to_le32(arena->flags);
 	super->version_major = cpu_to_le16(arena->version_major);
 	super->version_minor = cpu_to_le16(arena->version_minor);
diff --git a/drivers/nvdimm/btt_devs.c b/drivers/nvdimm/btt_devs.c
index 18e0663e922c..242ae1c550ad 100644
--- a/drivers/nvdimm/btt_devs.c
+++ b/drivers/nvdimm/btt_devs.c
@@ -342,24 +342,37 @@ struct device *nd_btt_create(struct nd_region *nd_region)
 	return dev;
 }
 
+static bool uuid_is_null(u8 *uuid)
+{
+	static const u8 null_uuid[16];
+
+	return (memcmp(uuid, null_uuid, 16) == 0);
+}
+
 /**
  * nd_btt_arena_is_valid - check if the metadata layout is valid
  * @nd_btt:	device with BTT geometry and backing device info
  * @super:	pointer to the arena's info block being tested
  *
  * Check consistency of the btt info block with itself by validating
- * the checksum.
+ * the checksum, and with the parent namespace by verifying the
+ * parent_uuid contained in the info block with the one supplied in.
  *
  * Returns:
  * false for an invalid info block, true for a valid one
  */
 bool nd_btt_arena_is_valid(struct nd_btt *nd_btt, struct btt_sb *super)
 {
+	const u8 *parent_uuid = nd_dev_to_uuid(&nd_btt->ndns->dev);
 	u64 checksum;
 
 	if (memcmp(super->signature, BTT_SIG, BTT_SIG_LEN) != 0)
 		return false;
 
+	if (!uuid_is_null(super->parent_uuid))
+		if (memcmp(super->parent_uuid, parent_uuid, 16) != 0)
+			return false;
+
 	checksum = le64_to_cpu(super->checksum);
 	super->checksum = 0;
 	if (checksum != nd_btt_sb_checksum(super))
diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c
index fef0dd80d4ad..b18ffea9d85b 100644
--- a/drivers/nvdimm/namespace_devs.c
+++ b/drivers/nvdimm/namespace_devs.c
@@ -100,6 +100,26 @@ const char *nvdimm_namespace_disk_name(struct nd_namespace_common *ndns,
 }
 EXPORT_SYMBOL(nvdimm_namespace_disk_name);
 
+const u8 *nd_dev_to_uuid(struct device *dev)
+{
+	static const u8 null_uuid[16];
+
+	if (!dev)
+		return null_uuid;
+
+	if (is_namespace_pmem(dev)) {
+		struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
+
+		return nspm->uuid;
+	} else if (is_namespace_blk(dev)) {
+		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
+
+		return nsblk->uuid;
+	} else
+		return null_uuid;
+}
+EXPORT_SYMBOL(nd_dev_to_uuid);
+
 static ssize_t nstype_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
index 835263e47bb8..f9615824947b 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -217,4 +217,5 @@ static inline bool nd_iostat_start(struct bio *bio, unsigned long *start)
 }
 void nd_iostat_end(struct bio *bio, unsigned long start);
 resource_size_t nd_namespace_blk_validate(struct nd_namespace_blk *nsblk);
+const u8 *nd_dev_to_uuid(struct device *dev);
 #endif /* __ND_H__ */
-- 
cgit v1.2.3


From 708ab62bef1ed3a3cf065a4138bd87f5d083cfeb Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 10 Aug 2015 23:07:08 -0400
Subject: pmem: switch to devm_ allocations

Signed-off-by: Christoph Hellwig <hch@lst.de>
[djbw: tools/testing/nvdimm/ and memunmap_pmem support]
Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/nvdimm/pmem.c | 36 +++++++++++-------------------------
 1 file changed, 11 insertions(+), 25 deletions(-)

(limited to 'drivers')

diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index bcf48f133443..eb7552d939e1 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -119,7 +119,7 @@ static struct pmem_device *pmem_alloc(struct device *dev,
 {
 	struct pmem_device *pmem;
 
-	pmem = kzalloc(sizeof(*pmem), GFP_KERNEL);
+	pmem = devm_kzalloc(dev, sizeof(*pmem), GFP_KERNEL);
 	if (!pmem)
 		return ERR_PTR(-ENOMEM);
 
@@ -128,19 +128,16 @@ static struct pmem_device *pmem_alloc(struct device *dev,
 	if (!arch_has_pmem_api())
 		dev_warn(dev, "unable to guarantee persistence of writes\n");
 
-	if (!request_mem_region(pmem->phys_addr, pmem->size, dev_name(dev))) {
+	if (!devm_request_mem_region(dev, pmem->phys_addr, pmem->size,
+			dev_name(dev))) {
 		dev_warn(dev, "could not reserve region [0x%pa:0x%zx]\n",
 				&pmem->phys_addr, pmem->size);
-		kfree(pmem);
 		return ERR_PTR(-EBUSY);
 	}
 
-	pmem->virt_addr = memremap_pmem(pmem->phys_addr, pmem->size);
-	if (!pmem->virt_addr) {
-		release_mem_region(pmem->phys_addr, pmem->size);
-		kfree(pmem);
+	pmem->virt_addr = memremap_pmem(dev, pmem->phys_addr, pmem->size);
+	if (!pmem->virt_addr)
 		return ERR_PTR(-ENXIO);
-	}
 
 	return pmem;
 }
@@ -210,20 +207,12 @@ static int pmem_rw_bytes(struct nd_namespace_common *ndns,
 	return 0;
 }
 
-static void pmem_free(struct pmem_device *pmem)
-{
-	memunmap_pmem(pmem->virt_addr);
-	release_mem_region(pmem->phys_addr, pmem->size);
-	kfree(pmem);
-}
-
 static int nd_pmem_probe(struct device *dev)
 {
 	struct nd_region *nd_region = to_nd_region(dev->parent);
 	struct nd_namespace_common *ndns;
 	struct nd_namespace_io *nsio;
 	struct pmem_device *pmem;
-	int rc;
 
 	ndns = nvdimm_namespace_common_probe(dev);
 	if (IS_ERR(ndns))
@@ -236,16 +225,14 @@ static int nd_pmem_probe(struct device *dev)
 
 	dev_set_drvdata(dev, pmem);
 	ndns->rw_bytes = pmem_rw_bytes;
+
 	if (is_nd_btt(dev))
-		rc = nvdimm_namespace_attach_btt(ndns);
-	else if (nd_btt_probe(ndns, pmem) == 0) {
+		return nvdimm_namespace_attach_btt(ndns);
+
+	if (nd_btt_probe(ndns, pmem) == 0)
 		/* we'll come back as btt-pmem */
-		rc = -ENXIO;
-	} else
-		rc = pmem_attach_disk(ndns, pmem);
-	if (rc)
-		pmem_free(pmem);
-	return rc;
+		return -ENXIO;
+	return pmem_attach_disk(ndns, pmem);
 }
 
 static int nd_pmem_remove(struct device *dev)
@@ -256,7 +243,6 @@ static int nd_pmem_remove(struct device *dev)
 		nvdimm_namespace_detach_btt(to_nd_btt(dev)->ndns);
 	else
 		pmem_detach_disk(pmem);
-	pmem_free(pmem);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 7a67832c7e44c20935c5d6f2264035a0f7bf0d8f Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Wed, 19 Aug 2015 00:34:34 -0400
Subject: libnvdimm, e820: make CONFIG_X86_PMEM_LEGACY a tristate option

We currently register a platform device for e820 type-12 memory and
register a nvdimm bus beneath it.  Registering the platform device
triggers the device-core machinery to probe for a driver, but that
search currently comes up empty.  Building the nvdimm-bus registration
into the e820_pmem platform device registration in this way forces
libnvdimm to be built-in.  Instead, convert the built-in portion of
CONFIG_X86_PMEM_LEGACY to simply register a platform device and move the
rest of the logic to the driver for e820_pmem, for the following
reasons:

1/ Letting e820_pmem support be a module allows building and testing
   libnvdimm.ko changes without rebooting

2/ All the normal policy around modules can be applied to e820_pmem
   (unbind to disable and/or blacklisting the module from loading by
   default)

3/ Moving the driver to a generic location and converting it to scan
   "iomem_resource" rather than "e820.map" means any other architecture can
   take advantage of this simple nvdimm resource discovery mechanism by
   registering a resource named "Persistent Memory (legacy)"

Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/nvdimm/Makefile |  3 ++
 drivers/nvdimm/e820.c   | 86 +++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 89 insertions(+)
 create mode 100644 drivers/nvdimm/e820.c

(limited to 'drivers')

diff --git a/drivers/nvdimm/Makefile b/drivers/nvdimm/Makefile
index 594bb97c867a..9bf15db52dee 100644
--- a/drivers/nvdimm/Makefile
+++ b/drivers/nvdimm/Makefile
@@ -2,6 +2,7 @@ obj-$(CONFIG_LIBNVDIMM) += libnvdimm.o
 obj-$(CONFIG_BLK_DEV_PMEM) += nd_pmem.o
 obj-$(CONFIG_ND_BTT) += nd_btt.o
 obj-$(CONFIG_ND_BLK) += nd_blk.o
+obj-$(CONFIG_X86_PMEM_LEGACY) += nd_e820.o
 
 nd_pmem-y := pmem.o
 
@@ -9,6 +10,8 @@ nd_btt-y := btt.o
 
 nd_blk-y := blk.o
 
+nd_e820-y := e820.o
+
 libnvdimm-y := core.o
 libnvdimm-y += bus.o
 libnvdimm-y += dimm_devs.o
diff --git a/drivers/nvdimm/e820.c b/drivers/nvdimm/e820.c
new file mode 100644
index 000000000000..1b5743ad92db
--- /dev/null
+++ b/drivers/nvdimm/e820.c
@@ -0,0 +1,86 @@
+/*
+ * Copyright (c) 2015, Christoph Hellwig.
+ * Copyright (c) 2015, Intel Corporation.
+ */
+#include <linux/platform_device.h>
+#include <linux/libnvdimm.h>
+#include <linux/module.h>
+
+static const struct attribute_group *e820_pmem_attribute_groups[] = {
+	&nvdimm_bus_attribute_group,
+	NULL,
+};
+
+static const struct attribute_group *e820_pmem_region_attribute_groups[] = {
+	&nd_region_attribute_group,
+	&nd_device_attribute_group,
+	NULL,
+};
+
+static int e820_pmem_remove(struct platform_device *pdev)
+{
+	struct nvdimm_bus *nvdimm_bus = platform_get_drvdata(pdev);
+
+	nvdimm_bus_unregister(nvdimm_bus);
+	return 0;
+}
+
+static int e820_pmem_probe(struct platform_device *pdev)
+{
+	static struct nvdimm_bus_descriptor nd_desc;
+	struct device *dev = &pdev->dev;
+	struct nvdimm_bus *nvdimm_bus;
+	struct resource *p;
+
+	nd_desc.attr_groups = e820_pmem_attribute_groups;
+	nd_desc.provider_name = "e820";
+	nvdimm_bus = nvdimm_bus_register(dev, &nd_desc);
+	if (!nvdimm_bus)
+		goto err;
+	platform_set_drvdata(pdev, nvdimm_bus);
+
+	for (p = iomem_resource.child; p ; p = p->sibling) {
+		struct nd_region_desc ndr_desc;
+
+		if (strncmp(p->name, "Persistent Memory (legacy)", 26) != 0)
+			continue;
+
+		memset(&ndr_desc, 0, sizeof(ndr_desc));
+		ndr_desc.res = p;
+		ndr_desc.attr_groups = e820_pmem_region_attribute_groups;
+		ndr_desc.numa_node = NUMA_NO_NODE;
+		if (!nvdimm_pmem_region_create(nvdimm_bus, &ndr_desc))
+			goto err;
+	}
+
+	return 0;
+
+ err:
+	nvdimm_bus_unregister(nvdimm_bus);
+	dev_err(dev, "failed to register legacy persistent memory ranges\n");
+	return -ENXIO;
+}
+
+static struct platform_driver e820_pmem_driver = {
+	.probe = e820_pmem_probe,
+	.remove = e820_pmem_remove,
+	.driver = {
+		.name = "e820_pmem",
+	},
+};
+
+static __init int e820_pmem_init(void)
+{
+	return platform_driver_register(&e820_pmem_driver);
+}
+
+static __exit void e820_pmem_exit(void)
+{
+	platform_driver_unregister(&e820_pmem_driver);
+}
+
+MODULE_ALIAS("platform:e820_pmem*");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Intel Corporation");
+module_init(e820_pmem_init);
+module_exit(e820_pmem_exit);
-- 
cgit v1.2.3


From e2e05394e4a3420dab96f728df4531893494e15d Mon Sep 17 00:00:00 2001
From: Ross Zwisler <ross.zwisler@linux.intel.com>
Date: Tue, 18 Aug 2015 13:55:41 -0600
Subject: pmem, dax: have direct_access use __pmem annotation

Update the annotation for the kaddr pointer returned by direct_access()
so that it is a __pmem pointer.  This is consistent with the PMEM driver
and with how this direct_access() pointer is used in the DAX code.

Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/block/brd.c          |  4 ++--
 drivers/nvdimm/pmem.c        |  4 ++--
 drivers/s390/block/dcssblk.c | 10 ++++++----
 3 files changed, 10 insertions(+), 8 deletions(-)

(limited to 'drivers')

diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 64ab4951e9d6..c96402fd1560 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -371,7 +371,7 @@ static int brd_rw_page(struct block_device *bdev, sector_t sector,
 
 #ifdef CONFIG_BLK_DEV_RAM_DAX
 static long brd_direct_access(struct block_device *bdev, sector_t sector,
-			void **kaddr, unsigned long *pfn, long size)
+			void __pmem **kaddr, unsigned long *pfn, long size)
 {
 	struct brd_device *brd = bdev->bd_disk->private_data;
 	struct page *page;
@@ -381,7 +381,7 @@ static long brd_direct_access(struct block_device *bdev, sector_t sector,
 	page = brd_insert_page(brd, sector);
 	if (!page)
 		return -ENOSPC;
-	*kaddr = page_address(page);
+	*kaddr = (void __pmem *)page_address(page);
 	*pfn = page_to_pfn(page);
 
 	/*
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index eb7552d939e1..f3b629779266 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -92,7 +92,7 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector,
 }
 
 static long pmem_direct_access(struct block_device *bdev, sector_t sector,
-			      void **kaddr, unsigned long *pfn, long size)
+		      void __pmem **kaddr, unsigned long *pfn, long size)
 {
 	struct pmem_device *pmem = bdev->bd_disk->private_data;
 	size_t offset = sector << 9;
@@ -101,7 +101,7 @@ static long pmem_direct_access(struct block_device *bdev, sector_t sector,
 		return -ENODEV;
 
 	/* FIXME convert DAX to comprehend that this mapping has a lifetime */
-	*kaddr = (void __force *) pmem->virt_addr + offset;
+	*kaddr = pmem->virt_addr + offset;
 	*pfn = (pmem->phys_addr + offset) >> PAGE_SHIFT;
 
 	return pmem->size - offset;
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index da212813f2d5..2c5a397b9f3e 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -29,7 +29,7 @@ static int dcssblk_open(struct block_device *bdev, fmode_t mode);
 static void dcssblk_release(struct gendisk *disk, fmode_t mode);
 static void dcssblk_make_request(struct request_queue *q, struct bio *bio);
 static long dcssblk_direct_access(struct block_device *bdev, sector_t secnum,
-				 void **kaddr, unsigned long *pfn, long size);
+			 void __pmem **kaddr, unsigned long *pfn, long size);
 
 static char dcssblk_segments[DCSSBLK_PARM_LEN] = "\0";
 
@@ -879,18 +879,20 @@ fail:
 
 static long
 dcssblk_direct_access (struct block_device *bdev, sector_t secnum,
-			void **kaddr, unsigned long *pfn, long size)
+			void __pmem **kaddr, unsigned long *pfn, long size)
 {
 	struct dcssblk_dev_info *dev_info;
 	unsigned long offset, dev_sz;
+	void *addr;
 
 	dev_info = bdev->bd_disk->private_data;
 	if (!dev_info)
 		return -ENODEV;
 	dev_sz = dev_info->end - dev_info->start;
 	offset = secnum * 512;
-	*kaddr = (void *) (dev_info->start + offset);
-	*pfn = virt_to_phys(*kaddr) >> PAGE_SHIFT;
+	addr = (void *) (dev_info->start + offset);
+	*pfn = virt_to_phys(addr) >> PAGE_SHIFT;
+	*kaddr = (void __pmem *) addr;
 
 	return dev_sz - offset;
 }
-- 
cgit v1.2.3


From a06a7576526e10a99ea7721533e7f2df3e26baad Mon Sep 17 00:00:00 2001
From: yalin wang <yalin.wang2010@gmail.com>
Date: Thu, 27 Aug 2015 19:35:48 -0400
Subject: nvdimm: change to use generic kvfree()

Signed-off-by: yalin wang <yalin.wang2010@gmail.com>
Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/nvdimm/dimm_devs.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

(limited to 'drivers')

diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c
index c05eb807d674..651b8d19d324 100644
--- a/drivers/nvdimm/dimm_devs.c
+++ b/drivers/nvdimm/dimm_devs.c
@@ -241,10 +241,7 @@ void nvdimm_drvdata_release(struct kref *kref)
 		nvdimm_free_dpa(ndd, res);
 	nvdimm_bus_unlock(dev);
 
-	if (ndd->data && is_vmalloc_addr(ndd->data))
-		vfree(ndd->data);
-	else
-		kfree(ndd->data);
+	kvfree(ndd->data);
 	kfree(ndd);
 	put_device(dev);
 }
-- 
cgit v1.2.3


From 67a3e8fe90156d41cd480d3dfbb40f3bc007c262 Mon Sep 17 00:00:00 2001
From: Ross Zwisler <ross.zwisler@linux.intel.com>
Date: Thu, 27 Aug 2015 13:14:20 -0600
Subject: nd_blk: change aperture mapping from WC to WB

This should result in a pretty sizeable performance gain for reads.  For
rough comparison I did some simple read testing using PMEM to compare
reads of write combining (WC) mappings vs write-back (WB).  This was
done on a random lab machine.

PMEM reads from a write combining mapping:
	# dd of=/dev/null if=/dev/pmem0 bs=4096 count=100000
	100000+0 records in
	100000+0 records out
	409600000 bytes (410 MB) copied, 9.2855 s, 44.1 MB/s

PMEM reads from a write-back mapping:
	# dd of=/dev/null if=/dev/pmem0 bs=4096 count=1000000
	1000000+0 records in
	1000000+0 records out
	4096000000 bytes (4.1 GB) copied, 3.44034 s, 1.2 GB/s

To be able to safely support a write-back aperture I needed to add
support for the "read flush" _DSM flag, as outlined in the DSM spec:

http://pmem.io/documents/NVDIMM_DSM_Interface_Example.pdf

This flag tells the ND BLK driver that it needs to flush the cache lines
associated with the aperture after the aperture is moved but before any
new data is read.  This ensures that any stale cache lines from the
previous contents of the aperture will be discarded from the processor
cache, and the new data will be read properly from the DIMM.  We know
that the cache lines are clean and will be discarded without any
writeback because either a) the previous aperture operation was a read,
and we never modified the contents of the aperture, or b) the previous
aperture operation was a write and we must have written back the dirtied
contents of the aperture to the DIMM before the I/O was completed.

In order to add support for the "read flush" flag I needed to add a
generic routine to invalidate cache lines, mmio_flush_range().  This is
protected by the ARCH_HAS_MMIO_FLUSH Kconfig variable, and is currently
only supported on x86.

Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/acpi/Kconfig |  1 +
 drivers/acpi/nfit.c  | 55 +++++++++++++++++++++++++++++-----------------------
 drivers/acpi/nfit.h  | 16 ++++++++++-----
 3 files changed, 43 insertions(+), 29 deletions(-)

(limited to 'drivers')

diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 114cf48085ab..4baeb853e0c3 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -410,6 +410,7 @@ config ACPI_NFIT
 	tristate "ACPI NVDIMM Firmware Interface Table (NFIT)"
 	depends on PHYS_ADDR_T_64BIT
 	depends on BLK_DEV
+	depends on ARCH_HAS_MMIO_FLUSH
 	select LIBNVDIMM
 	help
 	  Infrastructure to probe ACPI 6 compliant platforms for
diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c
index 7c2638f914a9..56fff0141636 100644
--- a/drivers/acpi/nfit.c
+++ b/drivers/acpi/nfit.c
@@ -1017,7 +1017,7 @@ static u64 read_blk_stat(struct nfit_blk *nfit_blk, unsigned int bw)
 	if (mmio->num_lines)
 		offset = to_interleave_offset(offset, mmio);
 
-	return readq(mmio->base + offset);
+	return readq(mmio->addr.base + offset);
 }
 
 static void write_blk_ctl(struct nfit_blk *nfit_blk, unsigned int bw,
@@ -1042,11 +1042,11 @@ static void write_blk_ctl(struct nfit_blk *nfit_blk, unsigned int bw,
 	if (mmio->num_lines)
 		offset = to_interleave_offset(offset, mmio);
 
-	writeq(cmd, mmio->base + offset);
+	writeq(cmd, mmio->addr.base + offset);
 	wmb_blk(nfit_blk);
 
 	if (nfit_blk->dimm_flags & ND_BLK_DCR_LATCH)
-		readq(mmio->base + offset);
+		readq(mmio->addr.base + offset);
 }
 
 static int acpi_nfit_blk_single_io(struct nfit_blk *nfit_blk,
@@ -1078,11 +1078,16 @@ static int acpi_nfit_blk_single_io(struct nfit_blk *nfit_blk,
 		}
 
 		if (rw)
-			memcpy_to_pmem(mmio->aperture + offset,
+			memcpy_to_pmem(mmio->addr.aperture + offset,
 					iobuf + copied, c);
-		else
+		else {
+			if (nfit_blk->dimm_flags & ND_BLK_READ_FLUSH)
+				mmio_flush_range((void __force *)
+					mmio->addr.aperture + offset, c);
+
 			memcpy_from_pmem(iobuf + copied,
-					mmio->aperture + offset, c);
+					mmio->addr.aperture + offset, c);
+		}
 
 		copied += c;
 		len -= c;
@@ -1129,7 +1134,10 @@ static void nfit_spa_mapping_release(struct kref *kref)
 
 	WARN_ON(!mutex_is_locked(&acpi_desc->spa_map_mutex));
 	dev_dbg(acpi_desc->dev, "%s: SPA%d\n", __func__, spa->range_index);
-	iounmap(spa_map->iomem);
+	if (spa_map->type == SPA_MAP_APERTURE)
+		memunmap((void __force *)spa_map->addr.aperture);
+	else
+		iounmap(spa_map->addr.base);
 	release_mem_region(spa->address, spa->length);
 	list_del(&spa_map->list);
 	kfree(spa_map);
@@ -1175,7 +1183,7 @@ static void __iomem *__nfit_spa_map(struct acpi_nfit_desc *acpi_desc,
 	spa_map = find_spa_mapping(acpi_desc, spa);
 	if (spa_map) {
 		kref_get(&spa_map->kref);
-		return spa_map->iomem;
+		return spa_map->addr.base;
 	}
 
 	spa_map = kzalloc(sizeof(*spa_map), GFP_KERNEL);
@@ -1191,20 +1199,19 @@ static void __iomem *__nfit_spa_map(struct acpi_nfit_desc *acpi_desc,
 	if (!res)
 		goto err_mem;
 
-	if (type == SPA_MAP_APERTURE) {
-		/*
-		 * TODO: memremap_pmem() support, but that requires cache
-		 * flushing when the aperture is moved.
-		 */
-		spa_map->iomem = ioremap_wc(start, n);
-	} else
-		spa_map->iomem = ioremap_nocache(start, n);
+	spa_map->type = type;
+	if (type == SPA_MAP_APERTURE)
+		spa_map->addr.aperture = (void __pmem *)memremap(start, n,
+							ARCH_MEMREMAP_PMEM);
+	else
+		spa_map->addr.base = ioremap_nocache(start, n);
+
 
-	if (!spa_map->iomem)
+	if (!spa_map->addr.base)
 		goto err_map;
 
 	list_add_tail(&spa_map->list, &acpi_desc->spa_maps);
-	return spa_map->iomem;
+	return spa_map->addr.base;
 
  err_map:
 	release_mem_region(start, n);
@@ -1267,7 +1274,7 @@ static int acpi_nfit_blk_get_flags(struct nvdimm_bus_descriptor *nd_desc,
 		nfit_blk->dimm_flags = flags.flags;
 	else if (rc == -ENOTTY) {
 		/* fall back to a conservative default */
-		nfit_blk->dimm_flags = ND_BLK_DCR_LATCH;
+		nfit_blk->dimm_flags = ND_BLK_DCR_LATCH | ND_BLK_READ_FLUSH;
 		rc = 0;
 	} else
 		rc = -ENXIO;
@@ -1307,9 +1314,9 @@ static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus,
 	/* map block aperture memory */
 	nfit_blk->bdw_offset = nfit_mem->bdw->offset;
 	mmio = &nfit_blk->mmio[BDW];
-	mmio->base = nfit_spa_map(acpi_desc, nfit_mem->spa_bdw,
+	mmio->addr.base = nfit_spa_map(acpi_desc, nfit_mem->spa_bdw,
 			SPA_MAP_APERTURE);
-	if (!mmio->base) {
+	if (!mmio->addr.base) {
 		dev_dbg(dev, "%s: %s failed to map bdw\n", __func__,
 				nvdimm_name(nvdimm));
 		return -ENOMEM;
@@ -1330,9 +1337,9 @@ static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus,
 	nfit_blk->cmd_offset = nfit_mem->dcr->command_offset;
 	nfit_blk->stat_offset = nfit_mem->dcr->status_offset;
 	mmio = &nfit_blk->mmio[DCR];
-	mmio->base = nfit_spa_map(acpi_desc, nfit_mem->spa_dcr,
+	mmio->addr.base = nfit_spa_map(acpi_desc, nfit_mem->spa_dcr,
 			SPA_MAP_CONTROL);
-	if (!mmio->base) {
+	if (!mmio->addr.base) {
 		dev_dbg(dev, "%s: %s failed to map dcr\n", __func__,
 				nvdimm_name(nvdimm));
 		return -ENOMEM;
@@ -1399,7 +1406,7 @@ static void acpi_nfit_blk_region_disable(struct nvdimm_bus *nvdimm_bus,
 	for (i = 0; i < 2; i++) {
 		struct nfit_blk_mmio *mmio = &nfit_blk->mmio[i];
 
-		if (mmio->base)
+		if (mmio->addr.base)
 			nfit_spa_unmap(acpi_desc, mmio->spa);
 	}
 	nd_blk_region_set_provider_data(ndbr, NULL);
diff --git a/drivers/acpi/nfit.h b/drivers/acpi/nfit.h
index f2c2bb751882..7e740156b9c2 100644
--- a/drivers/acpi/nfit.h
+++ b/drivers/acpi/nfit.h
@@ -41,6 +41,7 @@ enum nfit_uuids {
 };
 
 enum {
+	ND_BLK_READ_FLUSH = 1,
 	ND_BLK_DCR_LATCH = 2,
 };
 
@@ -117,12 +118,16 @@ enum nd_blk_mmio_selector {
 	DCR,
 };
 
+struct nd_blk_addr {
+	union {
+		void __iomem *base;
+		void __pmem  *aperture;
+	};
+};
+
 struct nfit_blk {
 	struct nfit_blk_mmio {
-		union {
-			void __iomem *base;
-			void __pmem  *aperture;
-		};
+		struct nd_blk_addr addr;
 		u64 size;
 		u64 base_offset;
 		u32 line_size;
@@ -149,7 +154,8 @@ struct nfit_spa_mapping {
 	struct acpi_nfit_system_address *spa;
 	struct list_head list;
 	struct kref kref;
-	void __iomem *iomem;
+	enum spa_map_type type;
+	struct nd_blk_addr addr;
 };
 
 static inline struct nfit_spa_mapping *to_spa_map(struct kref *kref)
-- 
cgit v1.2.3


From cb389b9c0e00c30c9daf20287f7d91e2466edbb1 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Fri, 7 Aug 2015 17:41:00 -0400
Subject: dax: drop size parameter to ->direct_access()

None of the implementations currently use it.  The common
bdev_direct_access() entry point handles all the size checks before
calling ->direct_access().

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/block/brd.c          | 6 +-----
 drivers/nvdimm/pmem.c        | 2 +-
 drivers/s390/block/dcssblk.c | 4 ++--
 3 files changed, 4 insertions(+), 8 deletions(-)

(limited to 'drivers')

diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index c96402fd1560..03c45c41bdfa 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -371,7 +371,7 @@ static int brd_rw_page(struct block_device *bdev, sector_t sector,
 
 #ifdef CONFIG_BLK_DEV_RAM_DAX
 static long brd_direct_access(struct block_device *bdev, sector_t sector,
-			void __pmem **kaddr, unsigned long *pfn, long size)
+			void __pmem **kaddr, unsigned long *pfn)
 {
 	struct brd_device *brd = bdev->bd_disk->private_data;
 	struct page *page;
@@ -384,10 +384,6 @@ static long brd_direct_access(struct block_device *bdev, sector_t sector,
 	*kaddr = (void __pmem *)page_address(page);
 	*pfn = page_to_pfn(page);
 
-	/*
-	 * TODO: If size > PAGE_SIZE, we could look to see if the next page in
-	 * the file happens to be mapped to the next page of physical RAM.
-	 */
 	return PAGE_SIZE;
 }
 #else
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index f3b629779266..3b5b9cb758b6 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -92,7 +92,7 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector,
 }
 
 static long pmem_direct_access(struct block_device *bdev, sector_t sector,
-		      void __pmem **kaddr, unsigned long *pfn, long size)
+		      void __pmem **kaddr, unsigned long *pfn)
 {
 	struct pmem_device *pmem = bdev->bd_disk->private_data;
 	size_t offset = sector << 9;
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index 2c5a397b9f3e..8c027a9e4e8a 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -29,7 +29,7 @@ static int dcssblk_open(struct block_device *bdev, fmode_t mode);
 static void dcssblk_release(struct gendisk *disk, fmode_t mode);
 static void dcssblk_make_request(struct request_queue *q, struct bio *bio);
 static long dcssblk_direct_access(struct block_device *bdev, sector_t secnum,
-			 void __pmem **kaddr, unsigned long *pfn, long size);
+			 void __pmem **kaddr, unsigned long *pfn);
 
 static char dcssblk_segments[DCSSBLK_PARM_LEN] = "\0";
 
@@ -879,7 +879,7 @@ fail:
 
 static long
 dcssblk_direct_access (struct block_device *bdev, sector_t secnum,
-			void __pmem **kaddr, unsigned long *pfn, long size)
+			void __pmem **kaddr, unsigned long *pfn)
 {
 	struct dcssblk_dev_info *dev_info;
 	unsigned long offset, dev_sz;
-- 
cgit v1.2.3


From 96601adb745186ccbcf5b078d4756f13381ec2af Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Mon, 24 Aug 2015 18:29:38 -0400
Subject: x86, pmem: clarify that ARCH_HAS_PMEM_API implies PMEM mapped WB

Given that a write-back (WB) mapping plus non-temporal stores is
expected to be the most efficient way to access PMEM, update the
definition of ARCH_HAS_PMEM_API to imply arch support for
WB-mapped-PMEM.  This is needed as a pre-requisite for adding PMEM to
the direct map and mapping it with struct page.

The above clarification for X86_64 means that memcpy_to_pmem() is
permitted to use the non-temporal arch_memcpy_to_pmem() rather than
needlessly fall back to default_memcpy_to_pmem() when the pcommit
instruction is not available.  When arch_memcpy_to_pmem() is not
guaranteed to flush writes out of cache, i.e. on older X86_32
implementations where non-temporal stores may just dirty cache,
ARCH_HAS_PMEM_API is simply disabled.

The default fall back for persistent memory handling remains.  Namely,
map it with the WT (write-through) cache-type and hope for the best.

arch_has_pmem_api() is updated to only indicate whether the arch
provides the proper helpers to meet the minimum "writes are visible
outside the cache hierarchy after memcpy_to_pmem() + wmb_pmem()".  Code
that cares whether wmb_pmem() actually flushes writes to pmem must now
call arch_has_wmb_pmem() directly.

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
[hch: set ARCH_HAS_PMEM_API=n on x86_32]
Reviewed-by: Christoph Hellwig <hch@lst.de>
[toshi: x86_32 compile fixes]
Signed-off-by: Toshi Kani <toshi.kani@hp.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/acpi/nfit.c   | 3 ++-
 drivers/nvdimm/pmem.c | 2 +-
 2 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'drivers')

diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c
index 56fff0141636..f61e69fa2ad1 100644
--- a/drivers/acpi/nfit.c
+++ b/drivers/acpi/nfit.c
@@ -20,6 +20,7 @@
 #include <linux/sort.h>
 #include <linux/pmem.h>
 #include <linux/io.h>
+#include <asm/cacheflush.h>
 #include "nfit.h"
 
 /*
@@ -1371,7 +1372,7 @@ static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus,
 			return -ENOMEM;
 	}
 
-	if (!arch_has_pmem_api() && !nfit_blk->nvdimm_flush)
+	if (!arch_has_wmb_pmem() && !nfit_blk->nvdimm_flush)
 		dev_warn(dev, "unable to guarantee persistence of writes\n");
 
 	if (mmio->line_size == 0)
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 3b5b9cb758b6..20bf122328da 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -125,7 +125,7 @@ static struct pmem_device *pmem_alloc(struct device *dev,
 
 	pmem->phys_addr = res->start;
 	pmem->size = resource_size(res);
-	if (!arch_has_pmem_api())
+	if (!arch_has_wmb_pmem())
 		dev_warn(dev, "unable to guarantee persistence of writes\n");
 
 	if (!devm_request_mem_region(dev, pmem->phys_addr, pmem->size,
-- 
cgit v1.2.3


From e1455744b27c9e6115c3508a7b2902157c2c4347 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Thu, 30 Jul 2015 17:57:47 -0400
Subject: libnvdimm, pfn: 'struct page' provider infrastructure

Implement the base infrastructure for libnvdimm PFN devices. Similar to
BTT devices they take a namespace as a backing device and layer
functionality on top. In this case the functionality is reserving space
for an array of 'struct page' entries to be handed out through
pfn_to_page(). For now this is just the basic libnvdimm-device-model for
configuring the base PFN device.

As the namespace claiming mechanism for PFN devices is mostly identical
to BTT devices drivers/nvdimm/claim.c is created to house the common
bits.

Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/nvdimm/Kconfig          |  22 +++
 drivers/nvdimm/Makefile         |   2 +
 drivers/nvdimm/btt.c            |   6 +-
 drivers/nvdimm/btt_devs.c       | 172 +-------------------
 drivers/nvdimm/claim.c          | 201 ++++++++++++++++++++++++
 drivers/nvdimm/namespace_devs.c |  34 +++-
 drivers/nvdimm/nd-core.h        |   9 ++
 drivers/nvdimm/nd.h             |  56 ++++++-
 drivers/nvdimm/pfn.h            |  35 +++++
 drivers/nvdimm/pfn_devs.c       | 336 ++++++++++++++++++++++++++++++++++++++++
 drivers/nvdimm/region.c         |   2 +
 drivers/nvdimm/region_devs.c    |  19 +++
 12 files changed, 717 insertions(+), 177 deletions(-)
 create mode 100644 drivers/nvdimm/claim.c
 create mode 100644 drivers/nvdimm/pfn.h
 create mode 100644 drivers/nvdimm/pfn_devs.c

(limited to 'drivers')

diff --git a/drivers/nvdimm/Kconfig b/drivers/nvdimm/Kconfig
index 72226acb5c0f..ace25b53b755 100644
--- a/drivers/nvdimm/Kconfig
+++ b/drivers/nvdimm/Kconfig
@@ -21,6 +21,7 @@ config BLK_DEV_PMEM
 	default LIBNVDIMM
 	depends on HAS_IOMEM
 	select ND_BTT if BTT
+	select ND_PFN if NVDIMM_PFN
 	help
 	  Memory ranges for PMEM are described by either an NFIT
 	  (NVDIMM Firmware Interface Table, see CONFIG_NFIT_ACPI), a
@@ -47,12 +48,16 @@ config ND_BLK
 	  (CONFIG_ACPI_NFIT), or otherwise exposes BLK-mode
 	  capabilities.
 
+config ND_CLAIM
+	bool
+
 config ND_BTT
 	tristate
 
 config BTT
 	bool "BTT: Block Translation Table (atomic sector updates)"
 	default y if LIBNVDIMM
+	select ND_CLAIM
 	help
 	  The Block Translation Table (BTT) provides atomic sector
 	  update semantics for persistent memory devices, so that
@@ -65,4 +70,21 @@ config BTT
 
 	  Select Y if unsure
 
+config ND_PFN
+	tristate
+
+config NVDIMM_PFN
+	bool "PFN: Map persistent (device) memory"
+	default LIBNVDIMM
+	select ND_CLAIM
+	help
+	  Map persistent memory, i.e. advertise it to the memory
+	  management sub-system.  By default persistent memory does
+	  not support direct I/O, RDMA, or any other usage that
+	  requires a 'struct page' to mediate an I/O request.  This
+	  driver allocates and initializes the infrastructure needed
+	  to support those use cases.
+
+	  Select Y if unsure
+
 endif
diff --git a/drivers/nvdimm/Makefile b/drivers/nvdimm/Makefile
index 9bf15db52dee..ea84d3c4e8e5 100644
--- a/drivers/nvdimm/Makefile
+++ b/drivers/nvdimm/Makefile
@@ -20,4 +20,6 @@ libnvdimm-y += region_devs.o
 libnvdimm-y += region.o
 libnvdimm-y += namespace_devs.o
 libnvdimm-y += label.o
+libnvdimm-$(CONFIG_ND_CLAIM) += claim.o
 libnvdimm-$(CONFIG_BTT) += btt_devs.o
+libnvdimm-$(CONFIG_NVDIMM_PFN) += pfn_devs.o
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index 19588291550b..028d2d137bc5 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -731,6 +731,7 @@ static int create_arenas(struct btt *btt)
 static int btt_arena_write_layout(struct arena_info *arena)
 {
 	int ret;
+	u64 sum;
 	struct btt_sb *super;
 	struct nd_btt *nd_btt = arena->nd_btt;
 	const u8 *parent_uuid = nd_dev_to_uuid(&nd_btt->ndns->dev);
@@ -770,7 +771,8 @@ static int btt_arena_write_layout(struct arena_info *arena)
 	super->info2off = cpu_to_le64(arena->info2off - arena->infooff);
 
 	super->flags = 0;
-	super->checksum = cpu_to_le64(nd_btt_sb_checksum(super));
+	sum = nd_sb_checksum((struct nd_gen_sb *) super);
+	super->checksum = cpu_to_le64(sum);
 
 	ret = btt_info_write(arena, super);
 
@@ -1422,8 +1424,6 @@ static int __init nd_btt_init(void)
 {
 	int rc;
 
-	BUILD_BUG_ON(sizeof(struct btt_sb) != SZ_4K);
-
 	btt_major = register_blkdev(0, "btt");
 	if (btt_major < 0)
 		return btt_major;
diff --git a/drivers/nvdimm/btt_devs.c b/drivers/nvdimm/btt_devs.c
index 242ae1c550ad..59ad54a63d9f 100644
--- a/drivers/nvdimm/btt_devs.c
+++ b/drivers/nvdimm/btt_devs.c
@@ -21,63 +21,13 @@
 #include "btt.h"
 #include "nd.h"
 
-static void __nd_btt_detach_ndns(struct nd_btt *nd_btt)
-{
-	struct nd_namespace_common *ndns = nd_btt->ndns;
-
-	dev_WARN_ONCE(&nd_btt->dev, !mutex_is_locked(&ndns->dev.mutex)
-			|| ndns->claim != &nd_btt->dev,
-			"%s: invalid claim\n", __func__);
-	ndns->claim = NULL;
-	nd_btt->ndns = NULL;
-	put_device(&ndns->dev);
-}
-
-static void nd_btt_detach_ndns(struct nd_btt *nd_btt)
-{
-	struct nd_namespace_common *ndns = nd_btt->ndns;
-
-	if (!ndns)
-		return;
-	get_device(&ndns->dev);
-	device_lock(&ndns->dev);
-	__nd_btt_detach_ndns(nd_btt);
-	device_unlock(&ndns->dev);
-	put_device(&ndns->dev);
-}
-
-static bool __nd_btt_attach_ndns(struct nd_btt *nd_btt,
-		struct nd_namespace_common *ndns)
-{
-	if (ndns->claim)
-		return false;
-	dev_WARN_ONCE(&nd_btt->dev, !mutex_is_locked(&ndns->dev.mutex)
-			|| nd_btt->ndns,
-			"%s: invalid claim\n", __func__);
-	ndns->claim = &nd_btt->dev;
-	nd_btt->ndns = ndns;
-	get_device(&ndns->dev);
-	return true;
-}
-
-static bool nd_btt_attach_ndns(struct nd_btt *nd_btt,
-		struct nd_namespace_common *ndns)
-{
-	bool claimed;
-
-	device_lock(&ndns->dev);
-	claimed = __nd_btt_attach_ndns(nd_btt, ndns);
-	device_unlock(&ndns->dev);
-	return claimed;
-}
-
 static void nd_btt_release(struct device *dev)
 {
 	struct nd_region *nd_region = to_nd_region(dev->parent);
 	struct nd_btt *nd_btt = to_nd_btt(dev);
 
 	dev_dbg(dev, "%s\n", __func__);
-	nd_btt_detach_ndns(nd_btt);
+	nd_detach_ndns(&nd_btt->dev, &nd_btt->ndns);
 	ida_simple_remove(&nd_region->btt_ida, nd_btt->id);
 	kfree(nd_btt->uuid);
 	kfree(nd_btt);
@@ -172,104 +122,15 @@ static ssize_t namespace_show(struct device *dev,
 	return rc;
 }
 
-static int namespace_match(struct device *dev, void *data)
-{
-	char *name = data;
-
-	return strcmp(name, dev_name(dev)) == 0;
-}
-
-static bool is_nd_btt_idle(struct device *dev)
-{
-	struct nd_region *nd_region = to_nd_region(dev->parent);
-	struct nd_btt *nd_btt = to_nd_btt(dev);
-
-	if (nd_region->btt_seed == dev || nd_btt->ndns || dev->driver)
-		return false;
-	return true;
-}
-
-static ssize_t __namespace_store(struct device *dev,
-		struct device_attribute *attr, const char *buf, size_t len)
-{
-	struct nd_btt *nd_btt = to_nd_btt(dev);
-	struct nd_namespace_common *ndns;
-	struct device *found;
-	char *name;
-
-	if (dev->driver) {
-		dev_dbg(dev, "%s: -EBUSY\n", __func__);
-		return -EBUSY;
-	}
-
-	name = kstrndup(buf, len, GFP_KERNEL);
-	if (!name)
-		return -ENOMEM;
-	strim(name);
-
-	if (strncmp(name, "namespace", 9) == 0 || strcmp(name, "") == 0)
-		/* pass */;
-	else {
-		len = -EINVAL;
-		goto out;
-	}
-
-	ndns = nd_btt->ndns;
-	if (strcmp(name, "") == 0) {
-		/* detach the namespace and destroy / reset the btt device */
-		nd_btt_detach_ndns(nd_btt);
-		if (is_nd_btt_idle(dev))
-			nd_device_unregister(dev, ND_ASYNC);
-		else {
-			nd_btt->lbasize = 0;
-			kfree(nd_btt->uuid);
-			nd_btt->uuid = NULL;
-		}
-		goto out;
-	} else if (ndns) {
-		dev_dbg(dev, "namespace already set to: %s\n",
-				dev_name(&ndns->dev));
-		len = -EBUSY;
-		goto out;
-	}
-
-	found = device_find_child(dev->parent, name, namespace_match);
-	if (!found) {
-		dev_dbg(dev, "'%s' not found under %s\n", name,
-				dev_name(dev->parent));
-		len = -ENODEV;
-		goto out;
-	}
-
-	ndns = to_ndns(found);
-	if (__nvdimm_namespace_capacity(ndns) < SZ_16M) {
-		dev_dbg(dev, "%s too small to host btt\n", name);
-		len = -ENXIO;
-		goto out_attach;
-	}
-
-	WARN_ON_ONCE(!is_nvdimm_bus_locked(&nd_btt->dev));
-	if (!nd_btt_attach_ndns(nd_btt, ndns)) {
-		dev_dbg(dev, "%s already claimed\n",
-				dev_name(&ndns->dev));
-		len = -EBUSY;
-	}
-
- out_attach:
-	put_device(&ndns->dev); /* from device_find_child */
- out:
-	kfree(name);
-	return len;
-}
-
 static ssize_t namespace_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t len)
 {
+	struct nd_btt *nd_btt = to_nd_btt(dev);
 	ssize_t rc;
 
 	nvdimm_bus_lock(dev);
 	device_lock(dev);
-	rc = __namespace_store(dev, attr, buf, len);
+	rc = nd_namespace_store(dev, &nd_btt->ndns, buf, len);
 	dev_dbg(dev, "%s: result: %zd wrote: %s%s", __func__,
 			rc, buf, buf[len - 1] == '\n' ? "" : "\n");
 	device_unlock(dev);
@@ -324,7 +185,7 @@ static struct device *__nd_btt_create(struct nd_region *nd_region,
 	dev->type = &nd_btt_device_type;
 	dev->groups = nd_btt_attribute_groups;
 	device_initialize(&nd_btt->dev);
-	if (ndns && !__nd_btt_attach_ndns(nd_btt, ndns)) {
+	if (ndns && !__nd_attach_ndns(&nd_btt->dev, ndns, &nd_btt->ndns)) {
 		dev_dbg(&ndns->dev, "%s failed, already claimed by %s\n",
 				__func__, dev_name(ndns->claim));
 		put_device(dev);
@@ -375,7 +236,7 @@ bool nd_btt_arena_is_valid(struct nd_btt *nd_btt, struct btt_sb *super)
 
 	checksum = le64_to_cpu(super->checksum);
 	super->checksum = 0;
-	if (checksum != nd_btt_sb_checksum(super))
+	if (checksum != nd_sb_checksum((struct nd_gen_sb *) super))
 		return false;
 	super->checksum = cpu_to_le64(checksum);
 
@@ -387,25 +248,6 @@ bool nd_btt_arena_is_valid(struct nd_btt *nd_btt, struct btt_sb *super)
 }
 EXPORT_SYMBOL(nd_btt_arena_is_valid);
 
-/*
- * nd_btt_sb_checksum: compute checksum for btt info block
- *
- * Returns a fletcher64 checksum of everything in the given info block
- * except the last field (since that's where the checksum lives).
- */
-u64 nd_btt_sb_checksum(struct btt_sb *btt_sb)
-{
-	u64 sum;
-	__le64 sum_save;
-
-	sum_save = btt_sb->checksum;
-	btt_sb->checksum = 0;
-	sum = nd_fletcher64(btt_sb, sizeof(*btt_sb), 1);
-	btt_sb->checksum = sum_save;
-	return sum;
-}
-EXPORT_SYMBOL(nd_btt_sb_checksum);
-
 static int __nd_btt_probe(struct nd_btt *nd_btt,
 		struct nd_namespace_common *ndns, struct btt_sb *btt_sb)
 {
@@ -453,7 +295,9 @@ int nd_btt_probe(struct nd_namespace_common *ndns, void *drvdata)
 	dev_dbg(&ndns->dev, "%s: btt: %s\n", __func__,
 			rc == 0 ? dev_name(dev) : "<none>");
 	if (rc < 0) {
-		__nd_btt_detach_ndns(to_nd_btt(dev));
+		struct nd_btt *nd_btt = to_nd_btt(dev);
+
+		__nd_detach_ndns(dev, &nd_btt->ndns);
 		put_device(dev);
 	}
 
diff --git a/drivers/nvdimm/claim.c b/drivers/nvdimm/claim.c
new file mode 100644
index 000000000000..e8f03b0e95e4
--- /dev/null
+++ b/drivers/nvdimm/claim.c
@@ -0,0 +1,201 @@
+/*
+ * Copyright(c) 2013-2015 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+#include <linux/device.h>
+#include <linux/sizes.h>
+#include "nd-core.h"
+#include "pfn.h"
+#include "btt.h"
+#include "nd.h"
+
+void __nd_detach_ndns(struct device *dev, struct nd_namespace_common **_ndns)
+{
+	struct nd_namespace_common *ndns = *_ndns;
+
+	dev_WARN_ONCE(dev, !mutex_is_locked(&ndns->dev.mutex)
+			|| ndns->claim != dev,
+			"%s: invalid claim\n", __func__);
+	ndns->claim = NULL;
+	*_ndns = NULL;
+	put_device(&ndns->dev);
+}
+
+void nd_detach_ndns(struct device *dev,
+		struct nd_namespace_common **_ndns)
+{
+	struct nd_namespace_common *ndns = *_ndns;
+
+	if (!ndns)
+		return;
+	get_device(&ndns->dev);
+	device_lock(&ndns->dev);
+	__nd_detach_ndns(dev, _ndns);
+	device_unlock(&ndns->dev);
+	put_device(&ndns->dev);
+}
+
+bool __nd_attach_ndns(struct device *dev, struct nd_namespace_common *attach,
+		struct nd_namespace_common **_ndns)
+{
+	if (attach->claim)
+		return false;
+	dev_WARN_ONCE(dev, !mutex_is_locked(&attach->dev.mutex)
+			|| *_ndns,
+			"%s: invalid claim\n", __func__);
+	attach->claim = dev;
+	*_ndns = attach;
+	get_device(&attach->dev);
+	return true;
+}
+
+bool nd_attach_ndns(struct device *dev, struct nd_namespace_common *attach,
+		struct nd_namespace_common **_ndns)
+{
+	bool claimed;
+
+	device_lock(&attach->dev);
+	claimed = __nd_attach_ndns(dev, attach, _ndns);
+	device_unlock(&attach->dev);
+	return claimed;
+}
+
+static int namespace_match(struct device *dev, void *data)
+{
+	char *name = data;
+
+	return strcmp(name, dev_name(dev)) == 0;
+}
+
+static bool is_idle(struct device *dev, struct nd_namespace_common *ndns)
+{
+	struct nd_region *nd_region = to_nd_region(dev->parent);
+	struct device *seed = NULL;
+
+	if (is_nd_btt(dev))
+		seed = nd_region->btt_seed;
+	else if (is_nd_pfn(dev))
+		seed = nd_region->pfn_seed;
+
+	if (seed == dev || ndns || dev->driver)
+		return false;
+	return true;
+}
+
+static void nd_detach_and_reset(struct device *dev,
+		struct nd_namespace_common **_ndns)
+{
+	/* detach the namespace and destroy / reset the device */
+	nd_detach_ndns(dev, _ndns);
+	if (is_idle(dev, *_ndns)) {
+		nd_device_unregister(dev, ND_ASYNC);
+	} else if (is_nd_btt(dev)) {
+		struct nd_btt *nd_btt = to_nd_btt(dev);
+
+		nd_btt->lbasize = 0;
+		kfree(nd_btt->uuid);
+		nd_btt->uuid = NULL;
+	} else if (is_nd_pfn(dev)) {
+		struct nd_pfn *nd_pfn = to_nd_pfn(dev);
+
+		kfree(nd_pfn->uuid);
+		nd_pfn->uuid = NULL;
+		nd_pfn->mode = PFN_MODE_NONE;
+	}
+}
+
+ssize_t nd_namespace_store(struct device *dev,
+		struct nd_namespace_common **_ndns, const char *buf,
+		size_t len)
+{
+	struct nd_namespace_common *ndns;
+	struct device *found;
+	char *name;
+
+	if (dev->driver) {
+		dev_dbg(dev, "%s: -EBUSY\n", __func__);
+		return -EBUSY;
+	}
+
+	name = kstrndup(buf, len, GFP_KERNEL);
+	if (!name)
+		return -ENOMEM;
+	strim(name);
+
+	if (strncmp(name, "namespace", 9) == 0 || strcmp(name, "") == 0)
+		/* pass */;
+	else {
+		len = -EINVAL;
+		goto out;
+	}
+
+	ndns = *_ndns;
+	if (strcmp(name, "") == 0) {
+		nd_detach_and_reset(dev, _ndns);
+		goto out;
+	} else if (ndns) {
+		dev_dbg(dev, "namespace already set to: %s\n",
+				dev_name(&ndns->dev));
+		len = -EBUSY;
+		goto out;
+	}
+
+	found = device_find_child(dev->parent, name, namespace_match);
+	if (!found) {
+		dev_dbg(dev, "'%s' not found under %s\n", name,
+				dev_name(dev->parent));
+		len = -ENODEV;
+		goto out;
+	}
+
+	ndns = to_ndns(found);
+	if (__nvdimm_namespace_capacity(ndns) < SZ_16M) {
+		dev_dbg(dev, "%s too small to host\n", name);
+		len = -ENXIO;
+		goto out_attach;
+	}
+
+	WARN_ON_ONCE(!is_nvdimm_bus_locked(dev));
+	if (!nd_attach_ndns(dev, ndns, _ndns)) {
+		dev_dbg(dev, "%s already claimed\n",
+				dev_name(&ndns->dev));
+		len = -EBUSY;
+	}
+
+ out_attach:
+	put_device(&ndns->dev); /* from device_find_child */
+ out:
+	kfree(name);
+	return len;
+}
+
+/*
+ * nd_sb_checksum: compute checksum for a generic info block
+ *
+ * Returns a fletcher64 checksum of everything in the given info block
+ * except the last field (since that's where the checksum lives).
+ */
+u64 nd_sb_checksum(struct nd_gen_sb *nd_gen_sb)
+{
+	u64 sum;
+	__le64 sum_save;
+
+	BUILD_BUG_ON(sizeof(struct btt_sb) != SZ_4K);
+	BUILD_BUG_ON(sizeof(struct nd_pfn_sb) != SZ_4K);
+	BUILD_BUG_ON(sizeof(struct nd_gen_sb) != SZ_4K);
+
+	sum_save = nd_gen_sb->checksum;
+	nd_gen_sb->checksum = 0;
+	sum = nd_fletcher64(nd_gen_sb, sizeof(*nd_gen_sb), 1);
+	nd_gen_sb->checksum = sum_save;
+	return sum;
+}
+EXPORT_SYMBOL(nd_sb_checksum);
diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c
index b18ffea9d85b..9303ca29be9b 100644
--- a/drivers/nvdimm/namespace_devs.c
+++ b/drivers/nvdimm/namespace_devs.c
@@ -82,8 +82,16 @@ const char *nvdimm_namespace_disk_name(struct nd_namespace_common *ndns,
 	struct nd_region *nd_region = to_nd_region(ndns->dev.parent);
 	const char *suffix = "";
 
-	if (ndns->claim && is_nd_btt(ndns->claim))
-		suffix = "s";
+	if (ndns->claim) {
+		if (is_nd_btt(ndns->claim))
+			suffix = "s";
+		else if (is_nd_pfn(ndns->claim))
+			suffix = "m";
+		else
+			dev_WARN_ONCE(&ndns->dev, 1,
+					"unknown claim type by %s\n",
+					dev_name(ndns->claim));
+	}
 
 	if (is_namespace_pmem(&ndns->dev) || is_namespace_io(&ndns->dev))
 		sprintf(name, "pmem%d%s", nd_region->id, suffix);
@@ -1255,12 +1263,22 @@ static const struct attribute_group *nd_namespace_attribute_groups[] = {
 struct nd_namespace_common *nvdimm_namespace_common_probe(struct device *dev)
 {
 	struct nd_btt *nd_btt = is_nd_btt(dev) ? to_nd_btt(dev) : NULL;
+	struct nd_pfn *nd_pfn = is_nd_pfn(dev) ? to_nd_pfn(dev) : NULL;
 	struct nd_namespace_common *ndns;
 	resource_size_t size;
 
-	if (nd_btt) {
-		ndns = nd_btt->ndns;
-		if (!ndns)
+	if (nd_btt || nd_pfn) {
+		struct device *host = NULL;
+
+		if (nd_btt) {
+			host = &nd_btt->dev;
+			ndns = nd_btt->ndns;
+		} else if (nd_pfn) {
+			host = &nd_pfn->dev;
+			ndns = nd_pfn->ndns;
+		}
+
+		if (!ndns || !host)
 			return ERR_PTR(-ENODEV);
 
 		/*
@@ -1271,12 +1289,12 @@ struct nd_namespace_common *nvdimm_namespace_common_probe(struct device *dev)
 		device_unlock(&ndns->dev);
 		if (ndns->dev.driver) {
 			dev_dbg(&ndns->dev, "is active, can't bind %s\n",
-					dev_name(&nd_btt->dev));
+					dev_name(host));
 			return ERR_PTR(-EBUSY);
 		}
-		if (dev_WARN_ONCE(&ndns->dev, ndns->claim != &nd_btt->dev,
+		if (dev_WARN_ONCE(&ndns->dev, ndns->claim != host,
 					"host (%s) vs claim (%s) mismatch\n",
-					dev_name(&nd_btt->dev),
+					dev_name(host),
 					dev_name(ndns->claim)))
 			return ERR_PTR(-ENXIO);
 	} else {
diff --git a/drivers/nvdimm/nd-core.h b/drivers/nvdimm/nd-core.h
index e1970c71ad1c..159aed532042 100644
--- a/drivers/nvdimm/nd-core.h
+++ b/drivers/nvdimm/nd-core.h
@@ -80,4 +80,13 @@ struct resource *nsblk_add_resource(struct nd_region *nd_region,
 int nvdimm_num_label_slots(struct nvdimm_drvdata *ndd);
 void get_ndd(struct nvdimm_drvdata *ndd);
 resource_size_t __nvdimm_namespace_capacity(struct nd_namespace_common *ndns);
+void nd_detach_ndns(struct device *dev, struct nd_namespace_common **_ndns);
+void __nd_detach_ndns(struct device *dev, struct nd_namespace_common **_ndns);
+bool nd_attach_ndns(struct device *dev, struct nd_namespace_common *attach,
+		struct nd_namespace_common **_ndns);
+bool __nd_attach_ndns(struct device *dev, struct nd_namespace_common *attach,
+		struct nd_namespace_common **_ndns);
+ssize_t nd_namespace_store(struct device *dev,
+		struct nd_namespace_common **_ndns, const char *buf,
+		size_t len);
 #endif /* __ND_CORE_H__ */
diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
index f9615824947b..8da2be1cecb8 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -29,6 +29,13 @@ enum {
 	ND_MAX_LANES = 256,
 	SECTOR_SHIFT = 9,
 	INT_LBASIZE_ALIGNMENT = 64,
+#if IS_ENABLED(CONFIG_NVDIMM_PFN)
+	ND_PFN_ALIGN = PAGES_PER_SECTION * PAGE_SIZE,
+	ND_PFN_MASK = ND_PFN_ALIGN - 1,
+#else
+	ND_PFN_ALIGN = 0,
+	ND_PFN_MASK = 0,
+#endif
 };
 
 struct nvdimm_drvdata {
@@ -92,8 +99,10 @@ struct nd_region {
 	struct device dev;
 	struct ida ns_ida;
 	struct ida btt_ida;
+	struct ida pfn_ida;
 	struct device *ns_seed;
 	struct device *btt_seed;
+	struct device *pfn_seed;
 	u16 ndr_mappings;
 	u64 ndr_size;
 	u64 ndr_start;
@@ -133,6 +142,22 @@ struct nd_btt {
 	int id;
 };
 
+enum nd_pfn_mode {
+	PFN_MODE_NONE,
+	PFN_MODE_RAM,
+	PFN_MODE_PMEM,
+};
+
+struct nd_pfn {
+	int id;
+	u8 *uuid;
+	struct device dev;
+	unsigned long npfns;
+	enum nd_pfn_mode mode;
+	struct nd_pfn_sb *pfn_sb;
+	struct nd_namespace_common *ndns;
+};
+
 enum nd_async_mode {
 	ND_SYNC,
 	ND_ASYNC,
@@ -159,8 +184,13 @@ int nvdimm_init_config_data(struct nvdimm_drvdata *ndd);
 int nvdimm_set_config_data(struct nvdimm_drvdata *ndd, size_t offset,
 		void *buf, size_t len);
 struct nd_btt *to_nd_btt(struct device *dev);
-struct btt_sb;
-u64 nd_btt_sb_checksum(struct btt_sb *btt_sb);
+
+struct nd_gen_sb {
+	char reserved[SZ_4K - 8];
+	__le64 checksum;
+};
+
+u64 nd_sb_checksum(struct nd_gen_sb *sb);
 #if IS_ENABLED(CONFIG_BTT)
 int nd_btt_probe(struct nd_namespace_common *ndns, void *drvdata);
 bool is_nd_btt(struct device *dev);
@@ -180,8 +210,30 @@ static inline struct device *nd_btt_create(struct nd_region *nd_region)
 {
 	return NULL;
 }
+#endif
 
+struct nd_pfn *to_nd_pfn(struct device *dev);
+#if IS_ENABLED(CONFIG_NVDIMM_PFN)
+int nd_pfn_probe(struct nd_namespace_common *ndns, void *drvdata);
+bool is_nd_pfn(struct device *dev);
+struct device *nd_pfn_create(struct nd_region *nd_region);
+#else
+static inline int nd_pfn_probe(struct nd_namespace_common *ndns, void *drvdata)
+{
+	return -ENODEV;
+}
+
+static inline bool is_nd_pfn(struct device *dev)
+{
+	return false;
+}
+
+static inline struct device *nd_pfn_create(struct nd_region *nd_region)
+{
+	return NULL;
+}
 #endif
+
 struct nd_region *to_nd_region(struct device *dev);
 int nd_region_to_nstype(struct nd_region *nd_region);
 int nd_region_register_namespaces(struct nd_region *nd_region, int *err);
diff --git a/drivers/nvdimm/pfn.h b/drivers/nvdimm/pfn.h
new file mode 100644
index 000000000000..cc243754acef
--- /dev/null
+++ b/drivers/nvdimm/pfn.h
@@ -0,0 +1,35 @@
+/*
+ * Copyright (c) 2014-2015, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#ifndef __NVDIMM_PFN_H
+#define __NVDIMM_PFN_H
+
+#include <linux/types.h>
+
+#define PFN_SIG_LEN 16
+#define PFN_SIG "NVDIMM_PFN_INFO\0"
+
+struct nd_pfn_sb {
+	u8 signature[PFN_SIG_LEN];
+	u8 uuid[16];
+	u8 parent_uuid[16];
+	__le32 flags;
+	__le16 version_major;
+	__le16 version_minor;
+	__le64 dataoff;
+	__le64 npfns;
+	__le32 mode;
+	u8 padding[4012];
+	__le64 checksum;
+};
+#endif /* __NVDIMM_PFN_H */
diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
new file mode 100644
index 000000000000..f708d63709a5
--- /dev/null
+++ b/drivers/nvdimm/pfn_devs.c
@@ -0,0 +1,336 @@
+/*
+ * Copyright(c) 2013-2015 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+#include <linux/blkdev.h>
+#include <linux/device.h>
+#include <linux/genhd.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include "nd-core.h"
+#include "pfn.h"
+#include "nd.h"
+
+static void nd_pfn_release(struct device *dev)
+{
+	struct nd_region *nd_region = to_nd_region(dev->parent);
+	struct nd_pfn *nd_pfn = to_nd_pfn(dev);
+
+	dev_dbg(dev, "%s\n", __func__);
+	nd_detach_ndns(&nd_pfn->dev, &nd_pfn->ndns);
+	ida_simple_remove(&nd_region->pfn_ida, nd_pfn->id);
+	kfree(nd_pfn->uuid);
+	kfree(nd_pfn);
+}
+
+static struct device_type nd_pfn_device_type = {
+	.name = "nd_pfn",
+	.release = nd_pfn_release,
+};
+
+bool is_nd_pfn(struct device *dev)
+{
+	return dev ? dev->type == &nd_pfn_device_type : false;
+}
+EXPORT_SYMBOL(is_nd_pfn);
+
+struct nd_pfn *to_nd_pfn(struct device *dev)
+{
+	struct nd_pfn *nd_pfn = container_of(dev, struct nd_pfn, dev);
+
+	WARN_ON(!is_nd_pfn(dev));
+	return nd_pfn;
+}
+EXPORT_SYMBOL(to_nd_pfn);
+
+static ssize_t mode_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nd_pfn *nd_pfn = to_nd_pfn(dev);
+
+	switch (nd_pfn->mode) {
+	case PFN_MODE_RAM:
+		return sprintf(buf, "ram\n");
+	case PFN_MODE_PMEM:
+		return sprintf(buf, "pmem\n");
+	default:
+		return sprintf(buf, "none\n");
+	}
+}
+
+static ssize_t mode_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t len)
+{
+	struct nd_pfn *nd_pfn = to_nd_pfn(dev);
+	ssize_t rc = 0;
+
+	device_lock(dev);
+	nvdimm_bus_lock(dev);
+	if (dev->driver)
+		rc = -EBUSY;
+	else {
+		size_t n = len - 1;
+
+		if (strncmp(buf, "pmem\n", n) == 0
+				|| strncmp(buf, "pmem", n) == 0) {
+			/* TODO: allocate from PMEM support */
+			rc = -ENOTTY;
+		} else if (strncmp(buf, "ram\n", n) == 0
+				|| strncmp(buf, "ram", n) == 0)
+			nd_pfn->mode = PFN_MODE_RAM;
+		else if (strncmp(buf, "none\n", n) == 0
+				|| strncmp(buf, "none", n) == 0)
+			nd_pfn->mode = PFN_MODE_NONE;
+		else
+			rc = -EINVAL;
+	}
+	dev_dbg(dev, "%s: result: %zd wrote: %s%s", __func__,
+			rc, buf, buf[len - 1] == '\n' ? "" : "\n");
+	nvdimm_bus_unlock(dev);
+	device_unlock(dev);
+
+	return rc ? rc : len;
+}
+static DEVICE_ATTR_RW(mode);
+
+static ssize_t uuid_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nd_pfn *nd_pfn = to_nd_pfn(dev);
+
+	if (nd_pfn->uuid)
+		return sprintf(buf, "%pUb\n", nd_pfn->uuid);
+	return sprintf(buf, "\n");
+}
+
+static ssize_t uuid_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t len)
+{
+	struct nd_pfn *nd_pfn = to_nd_pfn(dev);
+	ssize_t rc;
+
+	device_lock(dev);
+	rc = nd_uuid_store(dev, &nd_pfn->uuid, buf, len);
+	dev_dbg(dev, "%s: result: %zd wrote: %s%s", __func__,
+			rc, buf, buf[len - 1] == '\n' ? "" : "\n");
+	device_unlock(dev);
+
+	return rc ? rc : len;
+}
+static DEVICE_ATTR_RW(uuid);
+
+static ssize_t namespace_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nd_pfn *nd_pfn = to_nd_pfn(dev);
+	ssize_t rc;
+
+	nvdimm_bus_lock(dev);
+	rc = sprintf(buf, "%s\n", nd_pfn->ndns
+			? dev_name(&nd_pfn->ndns->dev) : "");
+	nvdimm_bus_unlock(dev);
+	return rc;
+}
+
+static ssize_t namespace_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t len)
+{
+	struct nd_pfn *nd_pfn = to_nd_pfn(dev);
+	ssize_t rc;
+
+	nvdimm_bus_lock(dev);
+	device_lock(dev);
+	rc = nd_namespace_store(dev, &nd_pfn->ndns, buf, len);
+	dev_dbg(dev, "%s: result: %zd wrote: %s%s", __func__,
+			rc, buf, buf[len - 1] == '\n' ? "" : "\n");
+	device_unlock(dev);
+	nvdimm_bus_unlock(dev);
+
+	return rc;
+}
+static DEVICE_ATTR_RW(namespace);
+
+static struct attribute *nd_pfn_attributes[] = {
+	&dev_attr_mode.attr,
+	&dev_attr_namespace.attr,
+	&dev_attr_uuid.attr,
+	NULL,
+};
+
+static struct attribute_group nd_pfn_attribute_group = {
+	.attrs = nd_pfn_attributes,
+};
+
+static const struct attribute_group *nd_pfn_attribute_groups[] = {
+	&nd_pfn_attribute_group,
+	&nd_device_attribute_group,
+	&nd_numa_attribute_group,
+	NULL,
+};
+
+static struct device *__nd_pfn_create(struct nd_region *nd_region,
+		u8 *uuid, enum nd_pfn_mode mode,
+		struct nd_namespace_common *ndns)
+{
+	struct nd_pfn *nd_pfn;
+	struct device *dev;
+
+	/* we can only create pages for contiguous ranged of pmem */
+	if (!is_nd_pmem(&nd_region->dev))
+		return NULL;
+
+	nd_pfn = kzalloc(sizeof(*nd_pfn), GFP_KERNEL);
+	if (!nd_pfn)
+		return NULL;
+
+	nd_pfn->id = ida_simple_get(&nd_region->pfn_ida, 0, 0, GFP_KERNEL);
+	if (nd_pfn->id < 0) {
+		kfree(nd_pfn);
+		return NULL;
+	}
+
+	nd_pfn->mode = mode;
+	if (uuid)
+		uuid = kmemdup(uuid, 16, GFP_KERNEL);
+	nd_pfn->uuid = uuid;
+	dev = &nd_pfn->dev;
+	dev_set_name(dev, "pfn%d.%d", nd_region->id, nd_pfn->id);
+	dev->parent = &nd_region->dev;
+	dev->type = &nd_pfn_device_type;
+	dev->groups = nd_pfn_attribute_groups;
+	device_initialize(&nd_pfn->dev);
+	if (ndns && !__nd_attach_ndns(&nd_pfn->dev, ndns, &nd_pfn->ndns)) {
+		dev_dbg(&ndns->dev, "%s failed, already claimed by %s\n",
+				__func__, dev_name(ndns->claim));
+		put_device(dev);
+		return NULL;
+	}
+	return dev;
+}
+
+struct device *nd_pfn_create(struct nd_region *nd_region)
+{
+	struct device *dev = __nd_pfn_create(nd_region, NULL, PFN_MODE_NONE,
+			NULL);
+
+	if (dev)
+		__nd_device_register(dev);
+	return dev;
+}
+
+static int nd_pfn_validate(struct nd_pfn *nd_pfn)
+{
+	struct nd_namespace_common *ndns = nd_pfn->ndns;
+	struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
+	struct nd_namespace_io *nsio;
+	u64 checksum, offset;
+
+	if (!pfn_sb || !ndns)
+		return -ENODEV;
+
+	if (!is_nd_pmem(nd_pfn->dev.parent))
+		return -ENODEV;
+
+	/* section alignment for simple hotplug */
+	if (nvdimm_namespace_capacity(ndns) < ND_PFN_ALIGN)
+		return -ENODEV;
+
+	if (nvdimm_read_bytes(ndns, SZ_4K, pfn_sb, sizeof(*pfn_sb)))
+		return -ENXIO;
+
+	if (memcmp(pfn_sb->signature, PFN_SIG, PFN_SIG_LEN) != 0)
+		return -ENODEV;
+
+	checksum = le64_to_cpu(pfn_sb->checksum);
+	pfn_sb->checksum = 0;
+	if (checksum != nd_sb_checksum((struct nd_gen_sb *) pfn_sb))
+		return -ENODEV;
+	pfn_sb->checksum = cpu_to_le64(checksum);
+
+	switch (le32_to_cpu(pfn_sb->mode)) {
+	case PFN_MODE_RAM:
+		break;
+	case PFN_MODE_PMEM:
+		/* TODO: allocate from PMEM support */
+		return -ENOTTY;
+	default:
+		return -ENXIO;
+	}
+
+	if (!nd_pfn->uuid) {
+		/* from probe we allocate */
+		nd_pfn->uuid = kmemdup(pfn_sb->uuid, 16, GFP_KERNEL);
+		if (!nd_pfn->uuid)
+			return -ENOMEM;
+	} else {
+		/* from init we validate */
+		if (memcmp(nd_pfn->uuid, pfn_sb->uuid, 16) != 0)
+			return -EINVAL;
+	}
+
+	/*
+	 * These warnings are verbose because they can only trigger in
+	 * the case where the physical address alignment of the
+	 * namespace has changed since the pfn superblock was
+	 * established.
+	 */
+	offset = le64_to_cpu(pfn_sb->dataoff);
+	nsio = to_nd_namespace_io(&ndns->dev);
+	if ((nsio->res.start + offset) & (ND_PFN_ALIGN - 1)) {
+		dev_err(&nd_pfn->dev,
+				"init failed: %s with offset %#llx not section aligned\n",
+				dev_name(&ndns->dev), offset);
+		return -EBUSY;
+	} else if (offset >= resource_size(&nsio->res)) {
+		dev_err(&nd_pfn->dev, "pfn array size exceeds capacity of %s\n",
+				dev_name(&ndns->dev));
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
+int nd_pfn_probe(struct nd_namespace_common *ndns, void *drvdata)
+{
+	int rc;
+	struct device *dev;
+	struct nd_pfn *nd_pfn;
+	struct nd_pfn_sb *pfn_sb;
+	struct nd_region *nd_region = to_nd_region(ndns->dev.parent);
+
+	if (ndns->force_raw)
+		return -ENODEV;
+
+	nvdimm_bus_lock(&ndns->dev);
+	dev = __nd_pfn_create(nd_region, NULL, PFN_MODE_NONE, ndns);
+	nvdimm_bus_unlock(&ndns->dev);
+	if (!dev)
+		return -ENOMEM;
+	dev_set_drvdata(dev, drvdata);
+	pfn_sb = kzalloc(sizeof(*pfn_sb), GFP_KERNEL);
+	nd_pfn = to_nd_pfn(dev);
+	nd_pfn->pfn_sb = pfn_sb;
+	rc = nd_pfn_validate(nd_pfn);
+	nd_pfn->pfn_sb = NULL;
+	kfree(pfn_sb);
+	dev_dbg(&ndns->dev, "%s: pfn: %s\n", __func__,
+			rc == 0 ? dev_name(dev) : "<none>");
+	if (rc < 0) {
+		__nd_detach_ndns(dev, &nd_pfn->ndns);
+		put_device(dev);
+	} else
+		__nd_device_register(&nd_pfn->dev);
+
+	return rc;
+}
+EXPORT_SYMBOL(nd_pfn_probe);
diff --git a/drivers/nvdimm/region.c b/drivers/nvdimm/region.c
index f28f78ccff19..7da63eac78ee 100644
--- a/drivers/nvdimm/region.c
+++ b/drivers/nvdimm/region.c
@@ -53,6 +53,7 @@ static int nd_region_probe(struct device *dev)
 		return -ENODEV;
 
 	nd_region->btt_seed = nd_btt_create(nd_region);
+	nd_region->pfn_seed = nd_pfn_create(nd_region);
 	if (err == 0)
 		return 0;
 
@@ -84,6 +85,7 @@ static int nd_region_remove(struct device *dev)
 	nvdimm_bus_lock(dev);
 	nd_region->ns_seed = NULL;
 	nd_region->btt_seed = NULL;
+	nd_region->pfn_seed = NULL;
 	dev_set_drvdata(dev, NULL);
 	nvdimm_bus_unlock(dev);
 
diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c
index 7384455792bf..da4338154ad2 100644
--- a/drivers/nvdimm/region_devs.c
+++ b/drivers/nvdimm/region_devs.c
@@ -345,6 +345,23 @@ static ssize_t btt_seed_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(btt_seed);
 
+static ssize_t pfn_seed_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nd_region *nd_region = to_nd_region(dev);
+	ssize_t rc;
+
+	nvdimm_bus_lock(dev);
+	if (nd_region->pfn_seed)
+		rc = sprintf(buf, "%s\n", dev_name(nd_region->pfn_seed));
+	else
+		rc = sprintf(buf, "\n");
+	nvdimm_bus_unlock(dev);
+
+	return rc;
+}
+static DEVICE_ATTR_RO(pfn_seed);
+
 static ssize_t read_only_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
@@ -373,6 +390,7 @@ static struct attribute *nd_region_attributes[] = {
 	&dev_attr_nstype.attr,
 	&dev_attr_mappings.attr,
 	&dev_attr_btt_seed.attr,
+	&dev_attr_pfn_seed.attr,
 	&dev_attr_read_only.attr,
 	&dev_attr_set_cookie.attr,
 	&dev_attr_available_size.attr,
@@ -744,6 +762,7 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus,
 	nd_region->numa_node = ndr_desc->numa_node;
 	ida_init(&nd_region->ns_ida);
 	ida_init(&nd_region->btt_ida);
+	ida_init(&nd_region->pfn_ida);
 	dev = &nd_region->dev;
 	dev_set_name(dev, "region%d", nd_region->id);
 	dev->parent = &nvdimm_bus->dev;
-- 
cgit v1.2.3


From 32ab0a3f51701cb37ab960635254d5f84ec3de0a Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Sat, 1 Aug 2015 02:16:37 -0400
Subject: libnvdimm, pmem: 'struct page' for pmem

Enable the pmem driver to handle PFN device instances.  Attaching a pmem
namespace to a pfn device triggers the driver to allocate and initialize
struct page entries for pmem.  Memory capacity for this allocation comes
exclusively from RAM for now which is suitable for low PMEM to RAM
ratios.  This mechanism will be expanded later for setting an "allocate
from PMEM" policy.

Cc: Boaz Harrosh <boaz@plexistor.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/nvdimm/Kconfig    |   1 +
 drivers/nvdimm/nd.h       |   6 ++
 drivers/nvdimm/pfn_devs.c |   9 +-
 drivers/nvdimm/pmem.c     | 203 +++++++++++++++++++++++++++++++++++++++++++---
 4 files changed, 202 insertions(+), 17 deletions(-)

(limited to 'drivers')

diff --git a/drivers/nvdimm/Kconfig b/drivers/nvdimm/Kconfig
index ace25b53b755..53c11621d5b1 100644
--- a/drivers/nvdimm/Kconfig
+++ b/drivers/nvdimm/Kconfig
@@ -76,6 +76,7 @@ config ND_PFN
 config NVDIMM_PFN
 	bool "PFN: Map persistent (device) memory"
 	default LIBNVDIMM
+	depends on ZONE_DEVICE
 	select ND_CLAIM
 	help
 	  Map persistent memory, i.e. advertise it to the memory
diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
index 8da2be1cecb8..83e5d0935012 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -217,6 +217,7 @@ struct nd_pfn *to_nd_pfn(struct device *dev);
 int nd_pfn_probe(struct nd_namespace_common *ndns, void *drvdata);
 bool is_nd_pfn(struct device *dev);
 struct device *nd_pfn_create(struct nd_region *nd_region);
+int nd_pfn_validate(struct nd_pfn *nd_pfn);
 #else
 static inline int nd_pfn_probe(struct nd_namespace_common *ndns, void *drvdata)
 {
@@ -232,6 +233,11 @@ static inline struct device *nd_pfn_create(struct nd_region *nd_region)
 {
 	return NULL;
 }
+
+static inline int nd_pfn_validate(struct nd_pfn *nd_pfn)
+{
+	return -ENODEV;
+}
 #endif
 
 struct nd_region *to_nd_region(struct device *dev);
diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
index f708d63709a5..3fd7d0d81a47 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/drivers/nvdimm/pfn_devs.c
@@ -228,7 +228,7 @@ struct device *nd_pfn_create(struct nd_region *nd_region)
 	return dev;
 }
 
-static int nd_pfn_validate(struct nd_pfn *nd_pfn)
+int nd_pfn_validate(struct nd_pfn *nd_pfn)
 {
 	struct nd_namespace_common *ndns = nd_pfn->ndns;
 	struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
@@ -286,10 +286,10 @@ static int nd_pfn_validate(struct nd_pfn *nd_pfn)
 	 */
 	offset = le64_to_cpu(pfn_sb->dataoff);
 	nsio = to_nd_namespace_io(&ndns->dev);
-	if ((nsio->res.start + offset) & (ND_PFN_ALIGN - 1)) {
+	if (nsio->res.start & ND_PFN_MASK) {
 		dev_err(&nd_pfn->dev,
-				"init failed: %s with offset %#llx not section aligned\n",
-				dev_name(&ndns->dev), offset);
+				"init failed: %s not section aligned\n",
+				dev_name(&ndns->dev));
 		return -EBUSY;
 	} else if (offset >= resource_size(&nsio->res)) {
 		dev_err(&nd_pfn->dev, "pfn array size exceeds capacity of %s\n",
@@ -299,6 +299,7 @@ static int nd_pfn_validate(struct nd_pfn *nd_pfn)
 
 	return 0;
 }
+EXPORT_SYMBOL(nd_pfn_validate);
 
 int nd_pfn_probe(struct nd_namespace_common *ndns, void *drvdata)
 {
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 20bf122328da..2f885e5d9c36 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -21,18 +21,24 @@
 #include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/module.h>
+#include <linux/memory_hotplug.h>
 #include <linux/moduleparam.h>
+#include <linux/vmalloc.h>
 #include <linux/slab.h>
 #include <linux/pmem.h>
 #include <linux/nd.h>
+#include "pfn.h"
 #include "nd.h"
 
 struct pmem_device {
 	struct request_queue	*pmem_queue;
 	struct gendisk		*pmem_disk;
+	struct nd_namespace_common *ndns;
 
 	/* One contiguous memory region per device */
 	phys_addr_t		phys_addr;
+	/* when non-zero this device is hosting a 'pfn' instance */
+	phys_addr_t		data_offset;
 	void __pmem		*virt_addr;
 	size_t			size;
 };
@@ -44,7 +50,7 @@ static void pmem_do_bvec(struct pmem_device *pmem, struct page *page,
 			sector_t sector)
 {
 	void *mem = kmap_atomic(page);
-	size_t pmem_off = sector << 9;
+	phys_addr_t pmem_off = sector * 512 + pmem->data_offset;
 	void __pmem *pmem_addr = pmem->virt_addr + pmem_off;
 
 	if (rw == READ) {
@@ -95,16 +101,23 @@ static long pmem_direct_access(struct block_device *bdev, sector_t sector,
 		      void __pmem **kaddr, unsigned long *pfn)
 {
 	struct pmem_device *pmem = bdev->bd_disk->private_data;
-	size_t offset = sector << 9;
-
-	if (!pmem)
-		return -ENODEV;
+	resource_size_t offset = sector * 512 + pmem->data_offset;
+	resource_size_t size;
+
+	if (pmem->data_offset) {
+		/*
+		 * Limit the direct_access() size to what is covered by
+		 * the memmap
+		 */
+		size = (pmem->size - offset) & ~ND_PFN_MASK;
+	} else
+		size = pmem->size - offset;
 
 	/* FIXME convert DAX to comprehend that this mapping has a lifetime */
 	*kaddr = pmem->virt_addr + offset;
 	*pfn = (pmem->phys_addr + offset) >> PAGE_SHIFT;
 
-	return pmem->size - offset;
+	return size;
 }
 
 static const struct block_device_operations pmem_fops = {
@@ -144,13 +157,16 @@ static struct pmem_device *pmem_alloc(struct device *dev,
 
 static void pmem_detach_disk(struct pmem_device *pmem)
 {
+	if (!pmem->pmem_disk)
+		return;
+
 	del_gendisk(pmem->pmem_disk);
 	put_disk(pmem->pmem_disk);
 	blk_cleanup_queue(pmem->pmem_queue);
 }
 
-static int pmem_attach_disk(struct nd_namespace_common *ndns,
-		struct pmem_device *pmem)
+static int pmem_attach_disk(struct device *dev,
+		struct nd_namespace_common *ndns, struct pmem_device *pmem)
 {
 	struct gendisk *disk;
 
@@ -177,8 +193,8 @@ static int pmem_attach_disk(struct nd_namespace_common *ndns,
 	disk->queue		= pmem->pmem_queue;
 	disk->flags		= GENHD_FL_EXT_DEVT;
 	nvdimm_namespace_disk_name(ndns, disk->disk_name);
-	disk->driverfs_dev = &ndns->dev;
-	set_capacity(disk, pmem->size >> 9);
+	disk->driverfs_dev = dev;
+	set_capacity(disk, (pmem->size - pmem->data_offset) / 512);
 	pmem->pmem_disk = disk;
 
 	add_disk(disk);
@@ -207,6 +223,154 @@ static int pmem_rw_bytes(struct nd_namespace_common *ndns,
 	return 0;
 }
 
+static int nd_pfn_init(struct nd_pfn *nd_pfn)
+{
+	struct nd_pfn_sb *pfn_sb = kzalloc(sizeof(*pfn_sb), GFP_KERNEL);
+	struct pmem_device *pmem = dev_get_drvdata(&nd_pfn->dev);
+	struct nd_namespace_common *ndns = nd_pfn->ndns;
+	struct nd_region *nd_region;
+	unsigned long npfns;
+	phys_addr_t offset;
+	u64 checksum;
+	int rc;
+
+	if (!pfn_sb)
+		return -ENOMEM;
+
+	nd_pfn->pfn_sb = pfn_sb;
+	rc = nd_pfn_validate(nd_pfn);
+	if (rc == 0 || rc == -EBUSY)
+		return rc;
+
+	/* section alignment for simple hotplug */
+	if (nvdimm_namespace_capacity(ndns) < ND_PFN_ALIGN
+			|| pmem->phys_addr & ND_PFN_MASK)
+		return -ENODEV;
+
+	nd_region = to_nd_region(nd_pfn->dev.parent);
+	if (nd_region->ro) {
+		dev_info(&nd_pfn->dev,
+				"%s is read-only, unable to init metadata\n",
+				dev_name(&nd_region->dev));
+		goto err;
+	}
+
+	memset(pfn_sb, 0, sizeof(*pfn_sb));
+	npfns = (pmem->size - SZ_8K) / SZ_4K;
+	/*
+	 * Note, we use 64 here for the standard size of struct page,
+	 * debugging options may cause it to be larger in which case the
+	 * implementation will limit the pfns advertised through
+	 * ->direct_access() to those that are included in the memmap.
+	 */
+	if (nd_pfn->mode == PFN_MODE_PMEM)
+		offset = ALIGN(SZ_8K + 64 * npfns, PMD_SIZE);
+	else if (nd_pfn->mode == PFN_MODE_RAM)
+		offset = SZ_8K;
+	else
+		goto err;
+
+	npfns = (pmem->size - offset) / SZ_4K;
+	pfn_sb->mode = cpu_to_le32(nd_pfn->mode);
+	pfn_sb->dataoff = cpu_to_le64(offset);
+	pfn_sb->npfns = cpu_to_le64(npfns);
+	memcpy(pfn_sb->signature, PFN_SIG, PFN_SIG_LEN);
+	memcpy(pfn_sb->uuid, nd_pfn->uuid, 16);
+	pfn_sb->version_major = cpu_to_le16(1);
+	checksum = nd_sb_checksum((struct nd_gen_sb *) pfn_sb);
+	pfn_sb->checksum = cpu_to_le64(checksum);
+
+	rc = nvdimm_write_bytes(ndns, SZ_4K, pfn_sb, sizeof(*pfn_sb));
+	if (rc)
+		goto err;
+
+	return 0;
+ err:
+	nd_pfn->pfn_sb = NULL;
+	kfree(pfn_sb);
+	return -ENXIO;
+}
+
+static int nvdimm_namespace_detach_pfn(struct nd_namespace_common *ndns)
+{
+	struct nd_pfn *nd_pfn = to_nd_pfn(ndns->claim);
+	struct pmem_device *pmem;
+
+	/* free pmem disk */
+	pmem = dev_get_drvdata(&nd_pfn->dev);
+	pmem_detach_disk(pmem);
+
+	/* release nd_pfn resources */
+	kfree(nd_pfn->pfn_sb);
+	nd_pfn->pfn_sb = NULL;
+
+	return 0;
+}
+
+static int nvdimm_namespace_attach_pfn(struct nd_namespace_common *ndns)
+{
+	struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
+	struct nd_pfn *nd_pfn = to_nd_pfn(ndns->claim);
+	struct device *dev = &nd_pfn->dev;
+	struct vmem_altmap *altmap;
+	struct nd_region *nd_region;
+	struct nd_pfn_sb *pfn_sb;
+	struct pmem_device *pmem;
+	phys_addr_t offset;
+	int rc;
+
+	if (!nd_pfn->uuid || !nd_pfn->ndns)
+		return -ENODEV;
+
+	nd_region = to_nd_region(dev->parent);
+	rc = nd_pfn_init(nd_pfn);
+	if (rc)
+		return rc;
+
+	if (PAGE_SIZE != SZ_4K) {
+		dev_err(dev, "only supported on systems with 4K PAGE_SIZE\n");
+		return -ENXIO;
+	}
+	if (nsio->res.start & ND_PFN_MASK) {
+		dev_err(dev, "%s not memory hotplug section aligned\n",
+				dev_name(&ndns->dev));
+		return -ENXIO;
+	}
+
+	pfn_sb = nd_pfn->pfn_sb;
+	offset = le64_to_cpu(pfn_sb->dataoff);
+	nd_pfn->mode = le32_to_cpu(nd_pfn->pfn_sb->mode);
+	if (nd_pfn->mode == PFN_MODE_RAM) {
+		if (offset != SZ_8K)
+			return -EINVAL;
+		nd_pfn->npfns = le64_to_cpu(pfn_sb->npfns);
+		altmap = NULL;
+	} else {
+		rc = -ENXIO;
+		goto err;
+	}
+
+	/* establish pfn range for lookup, and switch to direct map */
+	pmem = dev_get_drvdata(dev);
+	memunmap_pmem(dev, pmem->virt_addr);
+	pmem->virt_addr = (void __pmem *)devm_memremap_pages(dev, &nsio->res);
+	if (IS_ERR(pmem->virt_addr)) {
+		rc = PTR_ERR(pmem->virt_addr);
+		goto err;
+	}
+
+	/* attach pmem disk in "pfn-mode" */
+	pmem->data_offset = offset;
+	rc = pmem_attach_disk(dev, ndns, pmem);
+	if (rc)
+		goto err;
+
+	return rc;
+ err:
+	nvdimm_namespace_detach_pfn(ndns);
+	return rc;
+}
+
 static int nd_pmem_probe(struct device *dev)
 {
 	struct nd_region *nd_region = to_nd_region(dev->parent);
@@ -223,16 +387,27 @@ static int nd_pmem_probe(struct device *dev)
 	if (IS_ERR(pmem))
 		return PTR_ERR(pmem);
 
+	pmem->ndns = ndns;
 	dev_set_drvdata(dev, pmem);
 	ndns->rw_bytes = pmem_rw_bytes;
 
 	if (is_nd_btt(dev))
 		return nvdimm_namespace_attach_btt(ndns);
 
-	if (nd_btt_probe(ndns, pmem) == 0)
+	if (is_nd_pfn(dev))
+		return nvdimm_namespace_attach_pfn(ndns);
+
+	if (nd_btt_probe(ndns, pmem) == 0) {
 		/* we'll come back as btt-pmem */
 		return -ENXIO;
-	return pmem_attach_disk(ndns, pmem);
+	}
+
+	if (nd_pfn_probe(ndns, pmem) == 0) {
+		/* we'll come back as pfn-pmem */
+		return -ENXIO;
+	}
+
+	return pmem_attach_disk(dev, ndns, pmem);
 }
 
 static int nd_pmem_remove(struct device *dev)
@@ -240,7 +415,9 @@ static int nd_pmem_remove(struct device *dev)
 	struct pmem_device *pmem = dev_get_drvdata(dev);
 
 	if (is_nd_btt(dev))
-		nvdimm_namespace_detach_btt(to_nd_btt(dev)->ndns);
+		nvdimm_namespace_detach_btt(pmem->ndns);
+	else if (is_nd_pfn(dev))
+		nvdimm_namespace_detach_pfn(pmem->ndns);
 	else
 		pmem_detach_disk(pmem);
 
-- 
cgit v1.2.3


From 004f1afbe199e6ab20805b95aefd83ccd24bc5c7 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Mon, 24 Aug 2015 19:20:23 -0400
Subject: libnvdimm, pmem: direct map legacy pmem by default

The expectation is that the legacy / non-standard pmem discovery method
(e820 type-12) will only ever be used to describe small quantities of
persistent memory.  Larger capacities will be described via the ACPI
NFIT.  When "allocate struct page from pmem" support is added this default
policy can be overridden by assigning a legacy pmem namespace to a pfn
device, however this would be only be necessary if a platform used the
legacy mechanism to define a very large range.

Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/nvdimm/e820.c           |  1 +
 drivers/nvdimm/namespace_devs.c | 35 ++++++++++++++++++++++++++++++-----
 drivers/nvdimm/nd.h             |  2 ++
 drivers/nvdimm/pmem.c           | 15 ++++++++++++---
 drivers/nvdimm/region_devs.c    |  1 +
 5 files changed, 46 insertions(+), 8 deletions(-)

(limited to 'drivers')

diff --git a/drivers/nvdimm/e820.c b/drivers/nvdimm/e820.c
index 1b5743ad92db..8282db2ef99e 100644
--- a/drivers/nvdimm/e820.c
+++ b/drivers/nvdimm/e820.c
@@ -49,6 +49,7 @@ static int e820_pmem_probe(struct platform_device *pdev)
 		ndr_desc.res = p;
 		ndr_desc.attr_groups = e820_pmem_region_attribute_groups;
 		ndr_desc.numa_node = NUMA_NO_NODE;
+		set_bit(ND_REGION_PAGEMAP, &ndr_desc.flags);
 		if (!nvdimm_pmem_region_create(nvdimm_bus, &ndr_desc))
 			goto err;
 	}
diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c
index 9303ca29be9b..0955b2cb10fe 100644
--- a/drivers/nvdimm/namespace_devs.c
+++ b/drivers/nvdimm/namespace_devs.c
@@ -13,6 +13,7 @@
 #include <linux/module.h>
 #include <linux/device.h>
 #include <linux/slab.h>
+#include <linux/pmem.h>
 #include <linux/nd.h>
 #include "nd-core.h"
 #include "nd.h"
@@ -76,11 +77,32 @@ static bool is_namespace_io(struct device *dev)
 	return dev ? dev->type == &namespace_io_device_type : false;
 }
 
+bool pmem_should_map_pages(struct device *dev)
+{
+	struct nd_region *nd_region = to_nd_region(dev->parent);
+
+	if (!IS_ENABLED(CONFIG_ZONE_DEVICE))
+		return false;
+
+	if (!test_bit(ND_REGION_PAGEMAP, &nd_region->flags))
+		return false;
+
+	if (is_nd_pfn(dev) || is_nd_btt(dev))
+		return false;
+
+#ifdef ARCH_MEMREMAP_PMEM
+	return ARCH_MEMREMAP_PMEM == MEMREMAP_WB;
+#else
+	return false;
+#endif
+}
+EXPORT_SYMBOL(pmem_should_map_pages);
+
 const char *nvdimm_namespace_disk_name(struct nd_namespace_common *ndns,
 		char *name)
 {
 	struct nd_region *nd_region = to_nd_region(ndns->dev.parent);
-	const char *suffix = "";
+	const char *suffix = NULL;
 
 	if (ndns->claim) {
 		if (is_nd_btt(ndns->claim))
@@ -93,13 +115,16 @@ const char *nvdimm_namespace_disk_name(struct nd_namespace_common *ndns,
 					dev_name(ndns->claim));
 	}
 
-	if (is_namespace_pmem(&ndns->dev) || is_namespace_io(&ndns->dev))
-		sprintf(name, "pmem%d%s", nd_region->id, suffix);
-	else if (is_namespace_blk(&ndns->dev)) {
+	if (is_namespace_pmem(&ndns->dev) || is_namespace_io(&ndns->dev)) {
+		if (!suffix && pmem_should_map_pages(&ndns->dev))
+			suffix = "m";
+		sprintf(name, "pmem%d%s", nd_region->id, suffix ? suffix : "");
+	} else if (is_namespace_blk(&ndns->dev)) {
 		struct nd_namespace_blk *nsblk;
 
 		nsblk = to_nd_namespace_blk(&ndns->dev);
-		sprintf(name, "ndblk%d.%d%s", nd_region->id, nsblk->id, suffix);
+		sprintf(name, "ndblk%d.%d%s", nd_region->id, nsblk->id,
+				suffix ? suffix : "");
 	} else {
 		return NULL;
 	}
diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
index 83e5d0935012..417e521d299c 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -100,6 +100,7 @@ struct nd_region {
 	struct ida ns_ida;
 	struct ida btt_ida;
 	struct ida pfn_ida;
+	unsigned long flags;
 	struct device *ns_seed;
 	struct device *btt_seed;
 	struct device *pfn_seed;
@@ -276,4 +277,5 @@ static inline bool nd_iostat_start(struct bio *bio, unsigned long *start)
 void nd_iostat_end(struct bio *bio, unsigned long start);
 resource_size_t nd_namespace_blk_validate(struct nd_namespace_blk *nsblk);
 const u8 *nd_dev_to_uuid(struct device *dev);
+bool pmem_should_map_pages(struct device *dev);
 #endif /* __ND_H__ */
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 2f885e5d9c36..c5ae2e579288 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -148,9 +148,18 @@ static struct pmem_device *pmem_alloc(struct device *dev,
 		return ERR_PTR(-EBUSY);
 	}
 
-	pmem->virt_addr = memremap_pmem(dev, pmem->phys_addr, pmem->size);
-	if (!pmem->virt_addr)
-		return ERR_PTR(-ENXIO);
+	if (pmem_should_map_pages(dev)) {
+		void *addr = devm_memremap_pages(dev, res);
+
+		if (IS_ERR(addr))
+			return addr;
+		pmem->virt_addr = (void __pmem *) addr;
+	} else {
+		pmem->virt_addr = memremap_pmem(dev, pmem->phys_addr,
+				pmem->size);
+		if (!pmem->virt_addr)
+			return ERR_PTR(-ENXIO);
+	}
 
 	return pmem;
 }
diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c
index da4338154ad2..529f3f02e7b2 100644
--- a/drivers/nvdimm/region_devs.c
+++ b/drivers/nvdimm/region_devs.c
@@ -758,6 +758,7 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus,
 	nd_region->provider_data = ndr_desc->provider_data;
 	nd_region->nd_set = ndr_desc->nd_set;
 	nd_region->num_lanes = ndr_desc->num_lanes;
+	nd_region->flags = ndr_desc->flags;
 	nd_region->ro = ro;
 	nd_region->numa_node = ndr_desc->numa_node;
 	ida_init(&nd_region->ns_ida);
-- 
cgit v1.2.3